Our latest publications - LTG

• Barnes, Jeremy Claude; Velldal, Erik & Øvrelid, Lilja (2020). Improving Sentiment Analysis with Multi-task Learning of Negation. Natural Language Engineering.  ISSN 1351-3249. Show summary

  Sentiment analysis is directly affected by compositional phenomena in language that act on the prior polarity of the words and phrases found in the text. Negation is the most prevalent of these phenomena and in order to correctly predict sentiment, a classifier must be able to identify negation and disentangle the effect that its scope has on the final polarity of a text. This paper proposes a multi-task approach to explicitly incorporate information about negation in sentiment analysis, which we show outperforms learning negation implicitly in a data-driven manner. We describe our approach, a cascading neural architecture with selective sharing of LSTM layers, and show that explicitly training the model with negation as an auxiliary task helps improve the main task of sentiment analysis. The effect is demonstrated across several different standard English-language data sets for both tasks and we analyze several aspects of our system related to its performance, varying types and amounts of input data and different multi-task setups.

• Hammer, Hugo Lewi; Riegler, Michael Alexander; Øvrelid, Lilja & Velldal, Erik (2019). THREAT: A Large Annotated Corpus for Detection of Violent Threats, In  Proceedings of Content Based Multimedia Information (CBMI 2019).  IEEE conference proceedings.  ISBN 978-1-7281-4673-7.
• Ravishankar, Vinit; Gökirmak, Memduh; Øvrelid, Lilja & Velldal, Erik (2019). Multilingual Probing of Deep Pre-Trained Contextual Encoders, In Joakim Nivre; Leon Derczynski; Filip Ginter; Bjørn Lindi; Stephan Oepen; Anders Søgaard & Jorg Tidemann (ed.),  Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing.  Linköping University Electronic Press.  ISBN 978-91-7929-999-6.  Article.  s 37 - 47
• Nooralahzadeh, Farhad; Lønning, Jan Tore & Øvrelid, Lilja (2019). Reinforcement-based denoising of distantly supervised NER with partial annotation, In  Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019).  Association for Computational Linguistics.  ISBN 978-1-950737-789.  Article.  s 225 - 234
• Barnes, Jeremy Claude & Klinger, Roman (2019). Embedding Projection for Targeted Cross-Lingual Sentiment: Model Comparisons and a Real-World Study. The journal of artificial intelligence research.  ISSN 1076-9757.
• Barnes, Jeremy Claude (2019). LTG-Oslo Hierarchical Multi-task Network: The importance of negation for document-level sentiment in Spanish. CEUR Workshop Proceedings.  ISSN 1613-0073. Show summary

  This paper details LTG-Oslo team's participation in the sentiment track of the NEGES 2019 evaluation campaign. We participated in the task with a hierarchical multi-task network, which used shared lower-layers in a deep BiLSTM to predict negation, while the higher layers were dedicated to predicting document-level sentiment. The multi-task component shows promise as a way to incorporate information on negation into deep neural sentiment classifiers, despite the fact that the absolute results on the test set were relatively low for a binary classification task.

• R. Atrio, Alex; Badia, Toni & Barnes, Jeremy Claude (2019). On the Effect of Word Order on Cross-lingual Sentiment Analysis. Revista de Procesamiento de Lenguaje Natural (SEPLN).  ISSN 1135-5948.
• Mæhlum, Petter; Barnes, Jeremy Claude; Øvrelid, Lilja & Velldal, Erik (2019). Annotating evaluative sentences for sentiment analysis: a dataset for Norwegian, In Mareike Hartmann & Barbara Plank (ed.),  Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa).  Linköping University Electronic Press.  ISBN 978-91-7929-995-8.  Artikkel.  s 121 - 130 Show summary

  This paper documents the creation of a large-scale dataset of evaluative sentences – i.e. both subjective and objective sentences that are found to be sentiment-bearing – based on mixed-domain professional reviews from various news-sources. We present both the annotation scheme and first results for classification experiments. The effort represents a step toward creating a Norwegian dataset for fine-grained sentiment analysis.

• Barnes, Jeremy Claude; Touileb, Samia; Øvrelid, Lilja & Velldal, Erik (2019). Lexicon information in neural sentiment analysis: a multi-task learning approach, In Mareike Hartmann & Barbara Plank (ed.),  Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa).  Linköping University Electronic Press.  ISBN 978-91-7929-995-8.  Artikkel.  s 175 - 186 Show summary

  This paper explores the use of multi-task learning (MTL) for incorporating external knowledge in neural models. Specifically, we show how MTL can enable a BiLSTM sentiment classifier to incorporate information from sentiment lexicons. Our MTL set-up is shown to improve model performance (compared to a single-task set-up) on both English and Norwegian sentence-level sentiment datasets. The paper also introduces a new sentiment lexicon for Norwegian.

• Kutuzov, Andrei & Kuzmenko, Elizaveta (2019). To Lemmatize or Not to Lemmatize: How Word Normalisation Affects ELMo Performance in Word Sense Disambiguation, In Joakim Nivre; Leon Derczynski; Filip Ginter; Bjørn Lindi; Stephan Oepen; Anders Søgaard & Jorg Tidemann (ed.),  Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing.  Linköping University Electronic Press.  ISBN 978-91-7929-999-6.  conference paper.  s 22 - 28 Show summary

  In this paper, we critically evaluate the widespread assumption that deep learning NLP models do not require lemmatized input. To test this, we trained versions of contextualised word embedding ELMo models on raw tokenized corpora and on the corpora with word tokens replaced by their lemmas. Then, these models were evaluated on the word sense disambiguation task. This was done for the English and Russian languages. The experiments showed that while lemmatization is indeed not necessary for English, the situation is different for Russian. It seems that for rich-morphology languages, using lemmatized training and testing data yields small but consistent improvements: at least for word sense disambiguation. This means that the decisions about text pre-processing before training ELMo should consider the linguistic nature of the language in question.

• Ravishankar, Vinit; Øvrelid, Lilja & Velldal, Erik (2019). Probing Multilingual Sentence Representations With X-Probe, In  Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019).  Association for Computational Linguistics.  ISBN 978-1-950737-35-2.  Chapter / article.  s 156 - 168 Show summary

  This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain. In doing so, we make two contributions: first, we provide datasets for multilingual probing, derived from Wikipedia, in five languages, viz. English, French, German, Spanish and Russian. Second, we evaluate six sentence encoders for each language, each trained by mapping sentence representations to English sentence representations, using sentences in a parallel corpus. We discover that cross-lingually mapped representations are often better at retaining certain linguistic information than representations derived from English encoders trained on natural language inference (NLI) as a downstream task.

• Barnes, Jeremy Claude; Øvrelid, Lilja & Velldal, Erik (2019). Sentiment analysis is not solved! Assessing and probing sentiment classification, In  Proceedings of the 2nd BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP.  Association for Computational Linguistics.  ISBN 978-1-950737-30-7.  article.  s 12 - 23 Show summary

  Neural methods for sentiment analysis have led to quantitative improvements over previous approaches, but these advances are not always accompanied with a thorough analysis of the qualitative differences. Therefore, it is not clear what outstanding conceptual challenges for sentiment analysis remain. In this work, we attempt to discover what challenges still prove a problem for sentiment classifiers for English and to provide a challenging dataset. We collect the subset of sentences that an (oracle) ensemble of state-of-the-art sentiment classifiers misclassify and then annotate them for 18 linguistic and paralinguistic phenomena, such as negation, sarcasm, modality, etc. Finally, we provide a case study that demonstrates the usefulness of the dataset to probe the performance of a given sentiment classifier with respect to linguistic phenomena.

• Kutuzov, Andrei; Dorgham, Mohammad; Oliynyk, Oleksiy; Biemann, Chris & Panchenko, Alexander (2019). Making Fast Graph-based Algorithms with Graph Metric Embeddings, In Anna Korhonen; David Traum & Lluís Màrquez (ed.),  Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.  Association for Computational Linguistics.  ISBN 978-1-950737-48-2.  conference paper.  s 3349 - 3355 Show summary

  Graph measures, such as node distances, are inefficient to compute. We explore dense vector representations as an effective way to approximate the same information. We introduce a simple yet efficient and effective approach for learning graph embeddings. Instead of directly operating on the graph structure, our method takes structural measures of pairwise node similarities into account and learns dense node representations reflecting user-defined graph distance measures, such as e.g. the shortest path distance or distance measures that take information beyond the graph structure into account. We demonstrate a speed-up of several orders of magnitude when predicting word similarity by vector operations on our embeddings as opposed to directly computing the respective path-based measures, while outperforming various other graph embeddings on semantic similarity and word sense disambiguation tasks.

• Rodina, Julia; Bakshandaeva, Daria; Fomin, Vadim; Kutuzov, Andrei; Touileb, Samia & Velldal, Erik (2019). Measuring Diachronic Evolution of Evaluative Adjectives with Word Embeddings: the Case for English, Norwegian, and Russian, In Nina Tahmasebi; Lars Borin; Adam Jatowt & Yang Xu (ed.),  Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change.  Association for Computational Linguistics.  ISBN 978-1-950737-31-4.  chapter.  s 202 - 209 Show summary

  We measure the intensity of diachronic semantic shifts in adjectives in English, Norwegian and Russian across 5 decades. This is done in order to test the hypothesis that evaluative adjectives are more prone to temporal semantic change. To this end, 6 different methods of quantifying semantic change are used. Frequency-controlled experimental results show that, depending on the particular method, evaluative adjectives either do not differ from other types of adjectives in terms of semantic change or appear to actually be less prone to shifting (particularly, to ‘jitter’-type shifting). Thus, in spite of many well-known examples of semantically changing evaluative adjectives (like ‘terrific’ or ‘incredible’), it seems that such cases are not specific to this particular type of words.

• Kutuzov, Andrei; Velldal, Erik & Øvrelid, Lilja (2019). One-to-X Analogical Reasoning on Word Embeddings: a Case for Diachronic Armed Conflict Prediction from News Texts, In Nina Tahmasebi; Lars Borin; Adam Jatowt & Yang Xu (ed.),  Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change.  Association for Computational Linguistics.  ISBN 978-1-950737-31-4.  chapter.  s 196 - 201 Show summary

  We extend the well-known word analogy task to a one-to-X formulation, including one-to-none cases, when no correct answer exists. The task is cast as a relation discovery problem and applied to historical armed conflicts datasets, attempting to predict new relations of type ‘location:armed-group’ based on data about past events. As the source of semantic information, we use diachronic word embedding models trained on English news texts. A simple technique to improve diachronic performance in such task is demonstrated, using a threshold based on a function of cosine distance to decrease the number of false positives; this approach is shown to be beneficial on two different corpora. Finally, we publish a ready-to-use test set for one-to-X analogy evaluation on historical armed conflicts data.

• Kutuzov, Andrei; Dorgham, Mohammad; Oliynyk, Oleksiy; Biemann, Chris & Panchenko, Alexander (2019). Learning Graph Embeddings from WordNet-based Similarity Measures, In Rada Mihalcea; Ekaterina Shutova; Lun-Wei Ku; Kilian Evang & Soujanya Poria (ed.),  Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019).  Association for Computational Linguistics.  ISBN 978-1-948087-93-3.  conference paper.  s 125 - 135 Show summary

  We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph distance measure, such as e.g. the shortest path distance or distance measures that take information beyond the graph structure into account. Evaluation of the proposed model on semantic similarity and word sense disambiguation tasks, using various WordNet-based similarity measures, show that our approach yields competitive results, outperforming strong graph embedding baselines. The model is computationally efficient, being orders of magnitude faster than the direct computation of graph-based distances.

• Fomin, Vadim; Bakshandaeva, Daria; Rodina, Julia & Kutuzov, Andrei (2019). Tracing Cultural Diachronic Semantic Shifts in Russian Using Word Embeddings: Test Sets and Baselines. Komp'yuternaya Lingvistika i Intellektual'nye Tekhnologii.  ISSN 2221-7932.  18, s 203- 218 Show summary

  The paper introduces manually annotated test sets for the task of tracing diachronic (temporal) semantic shifts in Russian. The two test sets are complementary in that the first one covers comparatively strong semantic changes occurring to nouns and adjectives from pre-Soviet to Soviet times, while the second one covers comparatively subtle socially and culturally determined shifts occurring in years from 2000 to 2014. Additionally, the second test set offers more granular classification of shifts degree, but is limited to only adjectives. The introduction of the test sets allowed us to evaluate several well-established algorithms of semantic shifts detection (posing this as a classification problem), most of which have never been tested on Russian material. All of these algorithms use distributional word embedding models trained on the corresponding in-domain corpora. The resulting scores provide solid comparison baselines for future studies tackling similar tasks. We publish the datasets, code and the trained models in order to facilitate further research in automatically detecting temporal semantic shifts for Russian words, with time periods of different granularities.

• Nikishina, Irina; Bakarov, Amir & Kutuzov, Andrei (2018). RusNLP: Semantic search engine for Russian NLP conference papers. Lecture Notes in Computer Science.  ISSN 0302-9743.  11179 LNCS, s 111- 120 . doi: 10.1007/978-3-030-11027-7_11
• Coltekin, Cagri & Kasicheyanula, Taraka Rama (2018). Drug-use Identification from Tweets with Word and Character N-grams, In  Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop and Shared Task.  Association for Computational Linguistics.  ISBN 978-1-948087-77-3.  Article.  s 52 - 53
• Berdicevskis, Aleksandrs; Coltekin, Cagri; Ehret, Katharina; von Prince, Kilu; Ross, Daniel; Thompson, Bill; Yan, Chunxiao; Demberg, Vera; Lupyan, Gary; Kasicheyanula, Taraka Rama & Bentz, Christian (2018). Using Universal Dependencies in cross-linguistic complexity research, In  Proceedings of the Second Workshop on Universal Dependencies (UDW 2018).  Association for Computational Linguistics.  ISBN 978-1-948087-780.  Article.  s 8 - 17
• Coltekin, Cagri; Kasicheyanula, Taraka Rama & Blaschke, Verena (2018). Tubingen-Oslo Team at the VarDial 2018 Evaluation Campaign: An Analysis of N-gram Features in Language Variety Identification, In  Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018).  Association for Computational Linguistics.  ISBN 978-1-948087-55-1.  Article.  s 55 - 65
• Vajjala, Sowmya & Kasicheyanula, Taraka Rama (2018). Experiments with Universal CEFR Classification, In  Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications.  Association for Computational Linguistics.  ISBN 978-1-948087-11-7.  Article.  s 147 - 153
• Coltekin, Cagri & Kasicheyanula, Taraka Rama (2018). Tübingen-Oslo at SemEval-2018 Task 2: SVMs perform better than RNNs in Emoji Prediction, In  Proceedings of the 12th International Workshop on Semantic Evaluation.  Association for Computational Linguistics.  ISBN 978-1-948087-20-9.  Article.  s 34 - 38
• Kasicheyanula, Taraka Rama & Coltekin, Cagri (2018). Tübingen-Oslo system at SIGMORPHON shared task on morphological inflection. A multi-tasking multilingual sequence to sequence model, In  Proceedings of the CoNLL SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection.  Association for Computational Linguistics.  ISBN 978-1-948087-83-4.  Article.  s 112 - 115
• Kasicheyanula, Taraka Rama (2018). Similarity dependent Chinese Restaurant Process for Cognate Identification in Multilingual Wordlists, In  Proceedings of the 22nd Conference on Computational Natural Language Learning.  Association for Computational Linguistics.  ISBN 978-1-948087-72-8.  Article.  s 271 - 281
• Kasicheyanula, Taraka Rama & Wichmann, Søren (2018). Towards identifying the optimal datasize for lexically-based Bayesian inference of linguistic phylogenies, In  Proceedings of the 27th International Conference on Computational Linguistics.  Association for Computational Linguistics.  ISBN 978-1-948087-50-6.  Article.  s 1578 - 1590
• Fares, Murhaf; Oepen, Stephan; Øvrelid, Lilja; Björne, Jari & Johansson, Richard (2018). The 2018 Shared Task on Extrinsic Parser Evaluation: On the Downstream Utility of English Universal Dependency Parsers, In Daniel Zeman & Jan Hajic (ed.),  Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies.  Association for Computational Linguistics.  ISBN 978-1-948087-82-7.  Article.  s 22 - 33 Show summary

  We summarize empirical results and tentative conclusions from the Second Extrinsic Parser Evaluation Initiative (EPE 2018). We review the basic task setup, downstream applications involved, and end-to-end results for seventeen participating parsers. Based on both quantitative and qualitative analysis, we correlate intrinsic evaluation results at different layers of morphsyntactic analysis with observed downstream behavior.

• Fares, Murhaf; Oepen, Stephan & Velldal, Erik (2018). Transfer and Multi-Task Learning for Noun–Noun Compound Interpretation, In Ellen Riloff (ed.),  Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.  Association for Computational Linguistics.  ISBN 978-1-948087-84-1.  Paper.  s 1488 - 1498 Show summary

  In this paper, we empirically evaluate the utility of transfer and multi-task learning on a challenging semantic classification task: semantic interpretation of noun--noun compounds. Through a comprehensive series of experiments and in-depth error analysis, we show that transfer learning via parameter initialization and multi-task learning via parameter sharing can help a neural classification model generalize over a highly skewed distribution of relations. Further, we demonstrate how dual annotation with two distinct sets of relations over the same set of compounds can be exploited to improve the overall accuracy of a neural classifier and its F1 scores on the less frequent, but more difficult relations.

• Touileb, Samia; Pedersen, Truls Andre & Sjøvaag, Helle (2018). Automatic identification of unknown names with specific roles, In Beatrice Alex; Stefania Degaetano-Ortlieb; Anna Feldman; Anna Kazantseva; Nils Reiter & Stan Szpakowicz (ed.),  Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature.  Association for Computational Linguistics.  ISBN 978-1-948087-61-2.  150–158.  s 150 - 158
• Stadsnes, Cathrine; Øvrelid, Lilja & Velldal, Erik (2018). Evaluating Semantic Vectors for Norwegian. NIK: Norsk Informatikkonferanse.  ISSN 1892-0713. Show summary

  In this article, we present two benchmark data sets for evaluating models of semantic word similarity for Norwegian. While such resources are available for English, they did not exist for Norwegian prior to this work. Furthermore, we produce large-coverage semantic vectors trained on the Norwegian Newspaper Corpus using several popular word embedding frameworks. Finally, we demonstrate the usefulness of the created resources for evaluating performance of different word embedding models on the tasks of analogical reasoning and synonym detection. The benchmark data sets and word embeddings are all made freely available.

• Lison, Pierre; Tiedemann, Jörg & Kouylekov, Milen (2018). OpenSubtitles 2018: Statistical rescoring of sentence alignments in large, noisy parallel corpora, In Nicoletta Calzolari; Khalid Choukri; Christopher Cieri; Thierry Declerck; Sara Goggi; Koiti Hasida; Hitoshi Isahara; Bente Maegaard; Joseph Mariani; Hélène Mazo; Asuncion Moreno; Jan Odijk; Stelios Piperidis & Takenobu Tokunaga (ed.),  Proceedings of the Eleventh International Conference on Language Resources and Evaluation.  European Language Resources Association.  ISBN 979-10-95546-00-9.  papers.  s 1742 - 1748 Show summary

  Movie and TV subtitles are a highly valuable resource for the compilation of parallel corpora thanks to their availability in large numbers and across many languages. However, the quality of the resulting sentence alignments is often lower than for other parallel corpora. This paper presents a new major release of the OpenSubtitles collection of parallel corpora, which is extracted from a total of 3.7 million subtitles spread over 60 languages. In addition to a substantial increase in the corpus size (about 30 % compared to the previous version), this new release associates explicit quality scores to each sentence alignment. These scores are determined by a statistical regression model based on simple language-independent features and estimated on a small sample of aligned sentence pairs. Evaluation results show that the model is able predict lexical translation probabilities with a root mean square error of 0.07 (coefficient of determination R2 = 0.47). Based on the scores produced by this regression model, the parallel corpora can be filtered to prune out alignments with a score below a given threshold.

• Bakarov, A; Kutuzov, Andrei & Nikishina, I (2018). Russian computational linguistics: Topical structure in 2007-2017 conference papers. Komp'yuternaya Lingvistika i Intellektual'nye Tekhnologii.  ISSN 2221-7932.  2018-May(17) Show summary

  Russian NLP community exists for at least several decades. However, academic works analyzing it are scarce. The present paper fills in this gap by topical modeling of the proceedings of three major Russian NLP conferences (Dialogue, AIST and AINL) for the years from 2007 to 2017. The resulting corpus consists of about 500 academic papers. We focus on the analysis of developing research trends manifested in topical drift over time. As a result, we show statistically how Russian NLP community interests are moving towards machine learning and how the Dialogue (as the largest venue) influences the whole computational linguistics landscape.

• Kasicheyanula, Taraka Rama (2018). Three tree priors and five datasets: A study of Indo-European phylogenetics. Language Dynamics and Change.  ISSN 2210-5824.  8(2), s 182- 218 . doi: 10.1163/22105832-00802005
• Nooralahzadeh, Farhad & Øvrelid, Lilja (2018). SIRIUS-LTG: An Entity Linking Approach to Fact Extraction and Verification, In  Proceedings of the First Workshop on Fact Extraction and VERification (FEVER).  Association for Computational Linguistics.  ISBN 978-1-948087-73-5.  Article.  s 119 - 123
• Bouma, Gosse; Hajic, Jan; Haug, Dag Trygve Truslew; Nivre, Joakim; Solberg, Per Erik & Øvrelid, Lilja (2018). Expletives in Universal Dependency Treebanks, In  Proceedings of the Second Workshop on Universal Dependencies (UDW 2018).  Association for Computational Linguistics.  ISBN 978-1-948087-780.  Artikkel.  s 18 - 26
• Kasicheyanula, Taraka Rama; Brekke, Pål Haugar; Nytrø, Øystein & Øvrelid, Lilja (2018). Iterative development of family history annotation guidelines using a synthetic corpus of clinical text, In  Proceedings of the 9th International Workshop on Health Text Mining and Information Analysis (LOUHI 2018).  Association for Computational Linguistics.  ISBN 978-1-948087-74-2.  Artikkel.  s 111 - 121
• Sadov, Mikhail A. & Kutuzov, Andrei (2018). Use of morphology in distributional word embedding models: Russian language case. Komp'yuternaya Lingvistika i Intellektual'nye Tekhnologii.  ISSN 2221-7932.  2018-May(17), s 1- 12
• Kutuzov, Andrei; Øvrelid, Lilja; Szymanski, Terrence & Velldal, Erik (2018). Diachronic word embeddings and semantic shifts: a survey, In  Proceedings of the 27th International Conference on Computational Linguistics.  Association for Computational Linguistics.  ISBN 978-1-948087-50-6.  conference paper.  s 1384 - 1397 Full text in Research Archive. Show summary

  Recent years have witnessed a surge of publications aimed at tracing temporal changes in lexical semantics using distributional methods, particularly prediction-based word embedding models. However, this vein of research lacks the cohesion, common terminology and shared practices of more established areas of natural language processing. In this paper, we survey the current state of academic research related to diachronic word embeddings and semantic shifts detection. We start with discussing the notion of semantic shifts, and then continue with an overview of the existing methods for tracing such time-related shifts with word embedding models. We propose several axes along which these methods can be compared, and outline the main challenges before this emerging subfield of NLP, as well as prospects and possible applications.

• Nooralahzadeh, Farhad & Øvrelid, Lilja (2018). Syntactic Dependency Representations in Neural Relation Classification, In Georgiana Dinu; Miguel Ballesteros; Avirup Sil; Sam Bowman; Wael Hamza; Anders Søgaard; Tahira Naseem & Yoav Goldberg (ed.),  Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP.  Association for Computational Linguistics.  ISBN 978-1-948087-42-1.  Article.
• Ustalov, Dmitry; Panchenko, Alexander; Kutuzov, Andrei; Biemann, Chris & Ponzetto, Simone (2018). Unsupervised Semantic Frame Induction using Triclustering, In  Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).  Association for Computational Linguistics.  ISBN 978-1-948087-34-6.  conference paper.  s 55 - 62 Full text in Research Archive. Show summary

  We use dependency triples automatically extracted from a Web-scale corpus to perform unsupervised semantic frame induction. We cast the frame induction problem as a triclustering problem that is a generalization of clustering for triadic data. Our replicable benchmarks demonstrate that the proposed graph-based approach, Triframes, shows state-of-the art results on this task on a FrameNet-derived dataset and performing on par with competitive methods on a verb class clustering task.

• Kutuzov, Andrei (2018). Russian Word Sense Induction by Clustering Averaged Word Embeddings. Komp'yuternaya Lingvistika i Intellektual'nye Tekhnologii.  ISSN 2221-7932.  2018-May(17), s 391- 403 Full text in Research Archive. Show summary

  The paper reports our participation in the shared task on word sense induction and disambiguation for the Russian language (RUSSE’2018). Our team was ranked 2nd for the wiki-wiki dataset (containing mostly homonyms) and 5th for the bts-rnc and active-dict datasets (containing mostly polysemous words) among all 19 participants. The method we employed was extremely naive. It implied representing contexts of ambiguous words as averaged word embedding vectors, using off-the-shelf pre-trained distributional models. Then, these vector representations were clustered with mainstream clustering techniques, thus producing the groups corresponding to the ambiguous word’ senses. As a side result, we show that word embedding models trained on small but balanced corpora can be superior to those trained on large but noisy data—not only in intrinsic evaluation, but also in downstream tasks like word sense induction.

• Nooralahzadeh, Farhad; Øvrelid, Lilja & Lønning, Jan Tore (2018). SIRIUS-LTG-UiO at SemEval-2018 Task 7: Convolutional Neural Networks with Shortest Dependency Paths for Semantic Relation Extraction and Classification in Scientific Papers, In  Proceedings of the 12th International Workshop on Semantic Evaluation.  Association for Computational Linguistics.  ISBN 978-1-948087-20-9.  Article.  s 805 - 811
• Nooralahzadeh, Farhad; Øvrelid, Lilja & Lønning, Jan Tore (2018). Evaluation of Domain-specific Word Embeddings using Knowledge Resources, In Nicoletta Calzolari; Khalid Choukri; Christopher Cieri; Thierry Declerck; Sara Goggi; Koiti Hasida; Hitoshi Isahara; Bente Maegaard; Joseph Mariani; Hélène Mazo; Asuncion Moreno; Jan Odijk; Stelios Piperidis & Takenobu Tokunaga (ed.),  Proceedings of the Eleventh International Conference on Language Resources and Evaluation.  European Language Resources Association.  ISBN 979-10-95546-00-9.  Article.  s 1438 - 1445 Show summary

  In this work we evaluate domain-specific embedding models induced from textual resources in the Oil and Gas domain. We conduct intrinsic and extrinsic evaluations of both general and domain-specific embeddings and we observe that constructing domain-specific word embeddings is worthwhile even with a considerably smaller corpus size. Although the intrinsic evaluation shows low performance in synonymy detection, an in-depth error analysis reveals the ability of these models to discover additional semantic relations such as hyponymy, co-hyponymy and relatedness in the target domain. Extrinsic evaluation of the embedding models is provided by a domain-specific sentence classification task, which we solve using a convolutional neural network. We further adapt embedding enhancement methods to provide vector representations for infrequent and unseen terms. Experiments show that the adapted technique can provide improvements both in intrinsic and extrinsic evaluation.

• Øvrelid, Lilja; Kåsen, Andre; Hagen, Kristin; Solberg, Per Erik; Johannessen, Janne Bondi & Nøklestad, Anders (2018). The LIA Treebank of Spoken Norwegian Dialects, In Nicoletta Calzolari; Khalid Choukri; Christopher Cieri; Thierry Declerck; Sara Goggi; Koiti Hasida; Hitoshi Isahara; Bente Maegaard; Joseph Mariani; Hélène Mazo; Asuncion Moreno; Jan Odijk; Stelios Piperidis & Takenobu Tokunaga (ed.),  Proceedings of the Eleventh International Conference on Language Resources and Evaluation.  European Language Resources Association.  ISBN 979-10-95546-00-9.  Article 642.  s 4482 - 4488 Full text in Research Archive. Show summary

  This article presents the LIA treebank of transcribed spoken Norwegian dialects. It consists of dialect recordings made in the period between 1950--1990, which have been digitised, transcribed, and subsequently annotated with morphological and dependency-style syntactic analysis as part of the LIA (Language Infrastructure made Accessible) project at the University of Oslo. In this article, we describe the LIA material of dialect recordings and its transcription, transliteration and further morphosyntactic annotation. We focus in particular on the extension of the native NDT annotation scheme to spoken language phenomena, such as pauses and various types of disfluencies, and present the subsequent conversion of the treebank to the Universal Dependencies scheme. The treebank currently consists of 13,608 tokens, distributed over 1396 segments taken from three different dialects of spoken Norwegian. The LIA treebank annotation is an on-going effort and future releases will extend on the current data set.

• Velldal, Erik; Øvrelid, Lilja; Bergem, Eivind Alexander; Stadsnes, Cathrine; Touileb, Samia & Jørgensen, Fredrik (2018). NoReC: The Norwegian Review Corpus, In Nicoletta Calzolari; Khalid Choukri; Christopher Cieri; Thierry Declerck; Sara Goggi; Koiti Hasida; Hitoshi Isahara; Bente Maegaard; Joseph Mariani; Hélène Mazo; Asuncion Moreno; Jan Odijk; Stelios Piperidis & Takenobu Tokunaga (ed.),  Proceedings of the Eleventh International Conference on Language Resources and Evaluation.  European Language Resources Association.  ISBN 979-10-95546-00-9.  Article.  s 4186 - 4191 Show summary

  This paper presents the Norwegian Review Corpus (NoReC), created for training and evaluating models for document-level sentiment analysis. The full-text reviews have been collected from major Norwegian news sources and cover a range of different domains, including literature, movies, video games, restaurants, music and theater, in addition to product reviews across a range of categories. Each review is labeled with a manually assigned score of 1–6, as provided by the rating of the original author. This first release of the corpus comprises more than 35,000 reviews. It is distributed using the CoNLL-U format, pre-processed using UDPipe, along with a rich set of metadata. The work reported in this paper forms part of the SANT initiative (Sentiment Analysis for Norwegian Text), a project seeking to provide open resources and tools for sentiment analysis and opinion mining for Norwegian.

• Lapponi, Emanuele; Søyland, Martin G.; Velldal, Erik & Oepen, Stephan (2018). The Talk of Norway: A Richly Annotated Corpus of the Norwegian Parliament, 1998–2016. Language Resources and Evaluation.  ISSN 1574-020X.  52(3), s 873- 893 . doi: 10.1007/s10579-018-9411-5 Show summary

  In this work we present the Talk of Norway (ToN) data set, a collection of Norwegian Parliament speeches from 1998 to 2016. Every speech is richly annotated with metadata harvested from different sources, and augmented with language type, sentence, token, lemma, part-of-speech, and morphological feature annotations. We also present a pilot study on party classification in the Norwegian Parliament, carried out in the context of a cross-faculty collaboration involving researchers from both Political Science and Computer Science. Our initial experiments demonstrate how the linguistic and institutional annotations in ToN can be used to gather insights on how different aspects of the political process affect classification.

• Kutuzov, Andrei & Kunilovskaya, Maria (2018). Size vs. Structure in Training Corpora for Word Embedding Models: Araneum Russicum Maximum and Russian National Corpus. Lecture Notes in Computer Science.  ISSN 0302-9743.  10716 LNCS, s 47- 58 . doi: 10.1007/978-3-319-73013-4_5 Show summary

  In this paper, we present a distributional word embedding model trained on one of the largest available Russian corpora: Araneum Russicum Maximum (over 10 billion words crawled from the web). We compare this model to the model trained on the Russian National Corpus (RNC). The two corpora are much different in their size and compilation procedures. We test these differences by evaluating the trained models against the Russian part of the Multilingual SimLex999 semantic similarity dataset. We detect and describe numerous issues in this dataset and publish a new corrected version. Aside from the already known fact that the RNC is generally a better training corpus than web corpora, we enumerate and explain fine differences in how the models process semantic similarity task, what parts of the evaluation set are difficult for particular models and why. Additionally, the learning curves for both models are described, showing that the RNC is generally more robust as training material for this task.

• Kasicheyanula, Taraka Rama & Vajjala, Sowmya (2017). A Dependency Treebank for Telugu, In Jan Hajič (ed.),  Proceedings of the 16th International Workshop on Treebanks and Linguistic Theories.  Association for Computational Linguistics.  ISBN 978-80-88132-04-2.  Article.  s 119 - 128
• Flickinger, Dan; Oepen, Stephan & Bender, Emily (2017). Sustainable Development and Refinement of Complex Linguistic Annotations at Scale, In Nancy Ide & James Pustejovsky (ed.),  Handbook of Linguistic Annotation.  Springer.  ISBN 978-94-024-0879-9.  Chapter.  s 353 - 377
• Kunilovskaya, Maria & Kutuzov, Andrei (2017). Universal Dependencies-based syntactic features in detecting human translation varieties, In Jan Hajič (ed.),  Proceedings of the 16th International Workshop on Treebanks and Linguistic Theories.  Association for Computational Linguistics.  ISBN 978-80-88132-04-2.  chapter.  s 27 - 36 Show summary

  In this paper, syntactic annotation is used to reveal linguistic properties of translations. We employ the Universal Dependencies framework to represent learner and professional translations of English mass-media texts into Russian (along with non-translated Russian texts of the same genre) with the aim to discover and describe syntactic specificity of translations produced at different levels of competence. The search for differences between varieties of translation and the native texts is augmented with the results obtained from a series of machine learning classifications experiments. We show that syntactic structures have considerable predictive power in translationese detection, on par with the known low-level lexical features.

• Eckart de Castilho, Richard; Ide, Nancy; Lapponi, Emanuele; Oepen, Stephan; Suderman, Keith; Velldal, Erik & Verhagen, Marc (2017). Representation and Interchange of Linguistic Annotation. An In-Depth, Side-by-Side Comparison of Three Designs, In Nathan Schneider & Nianwen Xue (ed.),  Proceedings of the 11th Linguistic Annotation Workshop.  Association for Computational Linguistics.  ISBN 978-1-945626-39-5.  Chapter.  s 67 - 75
• Smirnov, Ivan V.; Kuznetsova, Rita; Kopotev, Mikhail; Khazov, Andrey; Lyashevskaya, Olga; Ivanova, L. & Kutuzov, Andrei (2017). Evaluation tracks on plagiarism detection algorithms for the Russian language. Komp'yuternaya Lingvistika i Intellektual'nye Tekhnologii.  ISSN 2221-7932.  1(16), s 271- 283
• Lapponi, Emanuele; Oepen, Stephan & Øvrelid, Lilja (2017). EPE 2017: The Sherlock Negation Resolution Downstream Application, In Stephan Oepen (ed.),  Proceedings of the 2017 Shared Task on Extrinsic Parser Evaluation at the Fourth International Conference on Dependency Linguistics and the 15th International Conference on Parsing Technologies.  Association for Computational Linguistics.  ISBN 978-1-945626-74-6.  Article.  s 25 - 30
• Oepen, Stephan; Øvrelid, Lilja; Björne, Jari; Johansson, Richard; Lapponi, Emanuele; Ginter, Filip & Velldal, Erik (2017). The 2017 Shared Task on Extrinsic Parser Evaluation: Towards a Reusable Community Infrastructure, In Stephan Oepen (ed.),  Proceedings of the 2017 Shared Task on Extrinsic Parser Evaluation at the Fourth International Conference on Dependency Linguistics and the 15th International Conference on Parsing Technologies.  Association for Computational Linguistics.  ISBN 978-1-945626-74-6.  Article.  s 1 - 16
• Kutuzov, Andrei & Kuzmenko, Elizaveta (2017). Two centuries in two thousand words: Neural embedding models in detecting diachronic lexical changes, In  Quantitative Approaches to the Russian Language.  Routledge.  ISBN 9781138097155.  chapter. Show summary

  In this paper, we show how Continuous Bag-of-Words (Mikolov et al., 2013) models trained on time-separated sub-corpora of the Russian National Corpus can be used to detect automatically words that may have undergone semantic changes. Our central assumption is that online training of such models with new textual data results in a “drift” of word vectors in the semantic space. Given that vectors represent the “meaning” of entities, this drift can be taken to reflect semantic shifts in the words experiencing it. As a result, we were able to closely replicate manually compiled lists of semantically changed Russian words from the existing body of research and substantially extend them in a largely unsupervised way. This idea is one of the reasons for the title of this paper, which in a way serves as a complement to the “20 words” in (Daniel & Dobrushina, 2016).

• Kutuzov, Andrei; Velldal, Erik & Øvrelid, Lilja (2017). Temporal dynamics of semantic relations in word embeddings: an application to predicting armed conflict participants, In  Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.  Association for Computational Linguistics.  ISBN 978-1-945626-83-8.  chapter.  s 1825 - 1830 Full text in Research Archive. Show summary

  This paper deals with using word embedding models to trace the temporal dynamics of semantic relations between pairs of words. The set-up is similar to the well-known analogies task, but expanded with a time dimension. To this end, we apply incremental updating of the models with new training texts, including incremental vocabulary expansion, coupled with learned transformation matrices that let us map between members of the relation. The proposed approach is evaluated on the task of predicting insurgent armed groups based on geographical locations. The gold standard data for the time span 1994--2010 is extracted from the UCDP Armed Conflicts dataset. The results show that the method is feasible and outperforms the baselines, but also that important work still remains to be done.

• Kutuzov, Andrei; Velldal, Erik & Øvrelid, Lilja (2017). Tracing armed conflicts with diachronic word embedding models, In Tommaso Caselli (ed.),  Proceedings of the Events and Stories in the News Workshop.  Association for Computational Linguistics.  ISBN 978-1-945626-63-0.  Chapter.  s 31 - 36 Full text in Research Archive. Show summary

  Recent studies have shown that word embedding models can be used to trace time-related (diachronic) semantic shifts for particular words. In this paper, we evaluate some of these approaches on the new task of predicting the dynamics of global armed conflicts on a year-to-year basis, using a dataset from the field of conflict research as the gold standard and the Gigaword news corpus as the training data. The results show that much work still remains in extracting `cultural' semantic shifts from diachronic word embedding models. At the same time, we present a new task complete with an evaluation set and introduce the `anchor words' method which outperforms previous approaches on this data.

• Kunilovskaya, Maria & Kutuzov, Andrei (2017). Testing target text fluency: A machine learning approach to detecting syntactic translationese in English-Russian translation, In  New perspectives on cohesion and coherence: Implications for translation.  Language Science Press.  ISBN 978-3-946234-72-2.  Chapter 5.  s 75 - 103 Show summary

  This research is aimed at the semi-automatic detection of divergences in sentence structures between Russian translated texts and non-translations. We focus our attention on atypical syntactic features of translations, because they have a greater negative impact on the overall textual quality than lexical translationese. Inadequate syntactic structures bring about various issues with target text fluency, which reduces readability and the reader's chances to get to the text message. From a procedural viewpoint, faulty syntax implies more post-editing effort. In the framework of this research, we reveal cases of syntactic translationese as dissimilarities between patterns of selected morphosyntactic and syntactic features (such as part of speech and sentence length) in the context of sentence boundaries observed in comparable monolingual corpora of learner translated and non-translated texts in Russian. To establish these syntactic differences we resort to a machine learning approach as opposed to the usual statistical significance analyses. To this end we employ models that predict unnatural sentence boundaries in translations and highlight factors that are responsible for their `foreignness'. For the first stage of the experiment, we train a decision tree model to describe the contextual features of sentence boundaries in the reference corpus of Russian texts. At the second stage, we use the results of the first multifactorial analysis as indicators of learner translators' choices that run counter to the regularities of the standard language variety. The predictors and their combinations are evaluated as to their efficiency for this task. As a result we are able to extract translated sentences whose structure is atypical against Russian texts produced without the constraints of the translation process and which, therefore, can be tentatively considered less fluent. These sentences represent cases of translationese.

• Kutuzov, Andrei & Kuzmenko, Elizaveta (2017). WebVectors: A toolkit for building web interfaces for vector semantic models. Communications in Computer and Information Science.  ISSN 1865-0929.  661, s 155- 161 . doi: 10.1007/978-3-319-52920-2_15 Show summary

  The paper presents a free and open source toolkit which aim is to quickly deploy web services handling distributed vector models of semantics. It fills in the gap between training such models (many tools are already available for this) and dissemination of the results to general public. Our toolkit, WebVectors, provides all the necessary routines for organizing online access to querying trained models via modern web interface. We also describe two demo installations of the toolkit, featuring several efficient models for English, Russian and Norwegian.

• Kutuzov, Andrei (2017). Arbitrariness of Linguistic Sign Questioned: Correlation between Word Form and Meaning in Russian. Komp'yuternaya Lingvistika i Intellektual'nye Tekhnologii.  ISSN 2221-7932.  1(16), s 109- 120 Full text in Research Archive. Show summary

  In this paper, we present the results of preliminary experiments on finding the link between the surface forms of Russian nouns (as represented by their graphic forms) and their meanings (as represented by vectors in a distributional model trained on the Russian National Corpus). We show that there is a strongly significant correlation between these two sides of a linguistic sign (in our case, word). This correlation coefficient is equal to 0.03 as calculated on a set of 1 729 mono-syllabic nouns, and in some subsets of words starting with particular two-letter sequences the correlation raises as high as 0.57. The overall correlation value is higher than the one reported in similar experiments for English (0.016). Additionally, we report correlation values for the noun subsets related to different phonaesthemes, supposedly represented by the initial characters of these nouns.

• Enger, Martine; Velldal, Erik & Øvrelid, Lilja (2017). An open-source tool for negation detection: a maximum-margin approach, In Eduardo Blanco; Roser Morante & Roser Saurí (ed.),  Proceedings of the Workshop on Computational Semantics Beyond Events and Roles.  Association for Computational Linguistics.  ISBN 978-1-945626-49-4.  Artikkel W17-1810.  s 64 - 69 Show summary

  This paper presents an open-source toolkit for negation detection. It identifies negation cues and their corresponding scope in either raw or parsed text using maximum-margin classification. The system design draws on best practice from the existing literature on negation detection, aiming for a simple and portable system that still achieves competitive performance. Pre-trained models and experimental results are provided for English.

• Sand, Heidi Marion; Velldal, Erik & Øvrelid, Lilja (2017). Wordnet extension via word embeddings: Experiments on the Norwegian Wordnet, In Jörg Tiedemann (ed.),  Proceedings of the 21st Nordic Conference on Computational Linguistics (NoDaLiDa).  Linköping University Electronic Press.  ISBN 978-91-7685-601-7.  Article no. 042.  s 298 - 302 Full text in Research Archive. Show summary

  This paper describes the process of automatically adding synsets and hypernymy relations to an existing wordnet based on word embeddings computed for POStagged lemmas in a large news corpus, achieving exact match attachment accuracy of over 80%. The reported experiments are based on the Norwegian Wordnet, but the method is language independent and also applicable to other wordnets. Moreover, this study also represents the first documented experiments of the Norwegian Wordnet.

• Hohle, Petter; Øvrelid, Lilja & Velldal, Erik (2017). Optimizing a PoS Tagset for Norwegian Dependency Parsing, In Jörg Tiedemann (ed.),  Proceedings of the 21st Nordic Conference on Computational Linguistics (NoDaLiDa).  Linköping University Electronic Press.  ISBN 978-91-7685-601-7.  Article no. 017.  s 142 - 151 Full text in Research Archive. Show summary

  This paper reports on a suite of experiments that evaluates how the linguistic granularity of part-of-speech tagsets impacts the performance of tagging and syntactic dependency parsing. Our results show that parsing accuracy can be significantly improved by introducing more finegrained morphological information in the tagset, even if tagger accuracy is compromised. Our taggers and parsers are trained and tested using the annotations of the Norwegian Dependency Treebank.

• Velldal, Erik; Øvrelid, Lilja & Hohle, Petter (2017). Joint UD Parsing of Norwegian Bokmål and Nynorsk, In Jörg Tiedemann (ed.),  Proceedings of the 21st Nordic Conference on Computational Linguistics (NoDaLiDa).  Linköping University Electronic Press.  ISBN 978-91-7685-601-7.  Article no. 001.  s 1 - 10 Full text in Research Archive. Show summary

  This paper investigates interactions in parser performance for the two official standards for written Norwegian: Bokmål and Nynorsk. We demonstrate that while applying models across standards yields poor performance, combining the training data for both standards yields better results than previously achieved for each of them in isolation. This has immediate practical value for processing Norwegian, as it means that a single parsing pipeline is sufficient to cover both varieties, with no loss in accuracy. Based on the Norwegian Universal Dependencies treebank we present results for multiple taggers and parsers, experimenting with different ways of varying the training data given to the learners, including the use of machine translation.

• Lison, Pierre & Kutuzov, Andrei (2017). Redefining Context Windows for Word Embedding Models: An Experimental Study, In Jörg Tiedemann (ed.),  Proceedings of the 21st Nordic Conference on Computational Linguistics (NoDaLiDa).  Linköping University Electronic Press.  ISBN 978-91-7685-601-7.  chapter.  s 284 - 288 Full text in Research Archive. Show summary

  Distributional semantic models learn vector representations of words through the contexts they occur in. Although the choice of context (which often takes the form of a sliding window) has a direct influence on the resulting embeddings, the exact role of this model component is still not fully understood. This paper presents a systematic analysis of context windows based on a set of four distinct hyperparameters. We train continuous Skip- Gram models on two English-language corpora for various combinations of these hyper-parameters, and evaluate them on both lexical similarity and analogy tasks. Notable experimental results are the positive impact of cross-sentential contexts and the surprisingly good performance of right-context windows.

• Kutuzov, Andrei; Fares, Murhaf; Oepen, Stephan & Velldal, Erik (2017). Word vectors, reuse, and replicability: Towards a community repository of large-text resources, In Jörg Tiedemann (ed.),  Proceedings of the 21st Nordic Conference on Computational Linguistics (NoDaLiDa).  Linköping University Electronic Press.  ISBN 978-91-7685-601-7.  chapter.  s 271 - 276 Full text in Research Archive. Show summary

  This paper describes an emerging shared repository of large-text resources for creating word vectors, including pre-processed corpora and pre-trained vectors for a range of frameworks and configurations. This will facilitate reuse, rapid experimentation, and replicability of results.

• Kutuzov, Andrei; Kuzmenko, Elizaveta & Pivovarova, Lidia (2017). Clustering of Russian Adjective-Noun Constructions using Word Embeddings, In Lidia Pivovarova; Jakub Piskorski & Tomaž Erjavec (ed.),  Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing.  Association for Computational Linguistics.  ISBN 978-1-945626-45-6.  chapter.  s 3 - 13 Full text in Research Archive. Show summary

  This paper presents a method of automatic construction extraction from a large corpus of Russian. The term `construction' here means a multi-word expression in which a variable can be replaced with another word from the same semantic class, for example, 'a glass of [water/juice/milk]'. We deal with constructions that consist of a noun and its adjective modifier. We propose a method of grouping such constructions into semantic classes via 2-step clustering of word vectors in distributional models. We compare it with other clustering techniques and evaluate it against A Russian-English Collocational Dictionary of the Human Body that contains manually annotated groups of constructions with nouns denoting human body parts. The best performing method is used to cluster all adjective-noun bigrams in the Russian National Corpus. Results of this procedure are publicly available and can be used to build a Russian construction dictionary, accelerate theoretical studies of constructions as well as facilitate teaching Russian as a foreign language.

• Koslowa, Olga & Kutuzov, Andrei (2016). Improving Distributional Semantic Models Using Anaphora Resolution during Linguistic Preprocessing. Komp'yuternaya Lingvistika i Intellektual'nye Tekhnologii.  ISSN 2221-7932.  15, s 288- 299
• Kuhlmann, Marco & Oepen, Stephan (2016). Towards a catalogue of linguistic graph banks. Computational Linguistics.  ISSN 0891-2017.  42(4), s 819- 827 . doi: 10.1162/COLI_a_00268
• Oepen, Stephan; Kuhlmann, Marco; Miyao, Yusuke; Zeman, Daniel; Cinková, Silvie; Flickinger, Dan; Hajič, Jan; Ivanova, Angelina & Urešová, Zdeňka (2016). Towards Comparability of Linguistic Graph Banks for Semantic Parsing, In  Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).  European Language Resources Association.  ISBN 978-2-9517408-9-1.  Chapter.  s 3991 - 3995
• Read, Jonathon; Velldal, Erik; Cavazza, Marc & Georg, Gersende (2016). A corpus of clinical practice guidelines annotated with the importance of recommendations, In  Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).  European Language Resources Association.  ISBN 978-2-9517408-9-1.  Kapittel.  s 1724 - 1731
• Oepen, Stephan; Read, Jonathon; Scheffler, Tatjana; Sidarenka, Uladzimir; Stede, Manfred; Velldal, Erik & Øvrelid, Lilja (2016). OPT: Oslo–Potsdam–Teesside. Pipelining Rules, Rankers, and Classifier Ensembles for Shallow Discourse Parsing, In Nianwen Xue (ed.),  Proceedings of the CoNLL-16 Shared Task.  Association for Computational Linguistics.  ISBN 978-1-932432-66-4.  Chapter.  s 20 - 26
• Fjeld, Ruth E Vatvedt & Saidi, Arash (2016). Hvordan slippe inn i Platons hage?, I: Asgerd Gudiksen & Henrik Hovmark (red.),  Nordiske Studier i Leksikografi 13 Rapport fra 13. Konference om Leksikografi i Norden København 19.-22. mai 2015.  Nordisk forening for leksikografi.  ISBN 978-87-992447-6-8.  Generelt program.  s 313 - 326
• Fares, Murhaf (2016). A Dataset for Joint Noun-Noun Compound Bracketing and Interpretation, In He He; Tao Lei & Will Roberts (ed.),  The 54th Annual Meeting of the Association for Computational Linguistics - Proceedings of the Student Research Workshop.  Association for Computational Linguistics.  ISBN 978-1-945626-02-9.  Article.  s 72 - 79
• Kutuzov, Andrei; Kuzmenko, Elizaveta & Marakasova, Anna (2016). Exploration of register-dependent lexical semantics using word embeddings, In  Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities (LT4DH).  Association for Computational Linguistics.  ISBN 978-4-87974-708-2.  Chapter.  s 26 - 34
• Ivanova, Angelina; Oepen, Stephan; Dridan, Rebecca; Flickinger, Dan; Øvrelid, Lilja & Lapponi, Emanuele (2016). On different approaches to syntactic analysis into bi-lexical dependencies: An empirical comparison of direct, PCFG-based, and HPSG-based parsers. Journal of Language Modelling.  ISSN 2299-856X.  4(1), s 113- 144
• Stoyanchev, Svetlana; Lison, Pierre & Bangalore, Srinivas (2016). Rapid Prototyping of Form-driven Dialogue Systems Using an Open-source Framework, In Raquel Fernández & Wolfgang Minker (ed.),  Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue.  Association for Computational Linguistics.  ISBN 978-1-945626-23-4.  1.  s 216 - 219 Show summary

  Most human-machine communication for information access through speech, text and graphical interfaces are mediated by forms – i.e. lists of named fields. However, deploying form-filling dialogue systems still remains a challenging task due to the effort and skill required to author such systems. We describe an extension to the OpenDial framework that enables the rapid creation of functional dialogue systems by non-experts. The dialogue designer specifies the slots and their types as input and the tool generates a domain specification that drives a slot-filling dialogue system. The presented approach provides several benefits compared to traditional techniques based on flowcharts, such as the use of probabilistic reasoning and flexible grounding strategies.

• Lison, Pierre & Kennington, Casey (2016). OpenDial: A Toolkit for Developing Spoken Dialogue Systems with Probabilistic Rules, In Sameer Pradhan & Marianna Apidianaki (ed.),  Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.  Association for Computational Linguistics.  ISBN 978-1-945626-03-6.  1.  s 67 - 72 Show summary

  We present a new release of OpenDial, an open-source toolkit for building and evaluating spoken dialogue systems. The toolkit relies on an information-state architecture where the dialogue state is represented as a Bayesian network and acts as a shared memory for all system modules. The domain models are specified via probabilistic rules encoded in XML. OpenDial has been deployed in several application domains such as human–robot interaction, intelligent tutoring systems and multi-modal in-car driver assistants.

• Dragone, Paolo & Lison, Pierre (2016). Classification and Resolution of Non-Sentential Utterances in Dialogue. Italian Journal of Computational Linguistics.  ISSN 2499-4553.  2(1), s 45- 62 Show summary

  This article addresses the problems of classification and resolution of non-sentential utterances (NSUs) in dialogue. NSUs are utterances that do not have a complete sentential form but convey a full clausal meaning given the conversational context, such as "To the contrary!" or "How much?". The presented approach builds upon the work of Fernández, Ginzburg, and Lappin (2007), who provide a taxonomy of NSUs divided in 15 classes along with a small annotated corpus extracted from dialogue transcripts. The main part of this article focuses on the automatic classification of NSUs according to these classes. We show that a combination of novel linguistic features and active learning techniques yields a significant improvement in the classification accuracy over the state-of-the-art, and is able to mitigate the scarcity of labelled data. Based on this classifier, the article also presents a novel approach for the semantic resolution of NSUs in context using probabilistic rules.

• Wester, Aksel Ladegård; Øvrelid, Lilja; Velldal, Erik & Hammer, Hugo Lewi (2016). Threat detection in online discussions, In  Proceedings of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis WASSA@NAACL-HLT 2016 (WASSA 2016).  Association for Computational Linguistics.  ISBN 978-1-941643-82-2.  Artikkel.  s 66 - 71
• Kutuzov, Andrei; Velldal, Erik & Øvrelid, Lilja (2016). Redefining part-of-speech classes with distributional semantic models, In  Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL).  Association for Computational Linguistics.  ISBN 978-1-945626-19-7.  Chapter.  s 115 - 125 Full text in Research Archive.
• Øvrelid, Lilja & Hohle, Petter (2016). Universal Dependencies for Norwegian, In  Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).  European Language Resources Association.  ISBN 978-2-9517408-9-1.  Artikkel.  s 1579 - 1585
• Lison, Pierre & Tiedemann, Jörg (2016). OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles, In  Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).  European Language Resources Association.  ISBN 978-2-9517408-9-1.  1.  s 923 - 929 Full text in Research Archive. Show summary

  We present a new major release of the OpenSubtitles collection of parallel corpora. The release is compiled from a large database of movie and TV subtitles and includes a total of 1689 bitexts spanning 2.6 billion sentences across 60 languages. The release also incorporates a number of enhancements in the preprocessing and alignment of the subtitles, such as the automatic correction of OCR errors and the use of meta-data to estimate the quality of each subtitle and score subtitle pairs.

• Kutuzov, Andrei; Kopotev, Mikhail; Sviridenko, Tatyana & Ivanova, Lyubov (2016). Clustering Comparable Corpora of Russian and Ukrainian Academic Texts: Word Embeddings and Semantic Fingerprints, In  Proceedings of the Ninth Workshop on Building and Using Comparable Corpora, held at LREC-2016.  European Language Resources Association.  ISBN 978-2-9517408-9-1.  Conference paper.  s 3 - 10
• Kutuzov, Andrei & Kuzmenko, Elizaveta (2016). Neural Embedding Language Models in Semantic Clustering of Web Search Results, In  Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).  European Language Resources Association.  ISBN 978-2-9517408-9-1.  Conference paper.  s 3044 - 3048
• Kutuzov, Andrei & Kuzmenko, Elizaveta (2016). Cross-lingual Trends Detection for Named Entities in News Texts with Dynamic Neural Embedding Models, In  Proceedings of the First International Workshop on Recent Trends in News Information Retrieval co-located with 38th European Conference on Information Retrieval (ECIR 2016).  Technical University of Aachen.  ISBN 978-3-319-30671-1.  Chapter.  s 27 - 32
• Fares, Murhaf; Oepen, Stephan & Velldal, Erik (2015). Identifying Compounds: On The Role of Syntax, In Markus Dickinson; Erhard Hinrichs; Agnieszka Patejuk & Adam Przepiórkowski (ed.),  Proceedings of the Fourteenth Workshop on Treebanks and Linguistic Theories (TLT14).  Institute of Computer Science, Polish Academy of Sciences (IPI-PAN).  ISBN 978-83-63159-18-4.  Article.
• Alonso, Hector Martinez; Plank, Barbara; Skjærholt, Arne & Søgaard, Anders (2015). Learning to parse with IAA-weighted loss, In Rada Mihalcea; Joyce Chai & Anoop Sarkar (ed.),  Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.  Association for Computational Linguistics.  ISBN 978-1-941643-49-5.  Artikkel.  s 1357 - 1361
• Dragone, Paolo & Lison, Pierre (2015). An Active Learning Approach to the Classification of Non-Sentential Utterances, In Cristina Bosco; Sara Tonelli & Fabio Massimo Zanzotto (ed.),  Proceedings of the Second Italian Conference on Computational Linguistics.  CLiC-IT 2015.  ISBN 978-88-99200-62-6.  papers.  s 115 - 119 Show summary

  This paper addresses the problem of classification of non-sentential utterances (NSUs). NSUs are utterances that do not have a complete sentential form but convey a full clausal meaning given the dialogue context. We extend the approach of Fernández et al. (2007), which provide a taxonomy of NSUs and a small annotated corpus extracted from dialogue transcripts. This paper demonstrates how the combination of new linguistic features and active learning techniques can mitigate the scarcity of labelled data. The results show a significant improvement in the classification accuracy over the state-of-the-art.

View all works in Cristin

• Nivre, Joakim; Derczynski, Leon; Ginter, Filip; Lindi, Bjørn; Oepen, Stephan; Søgaard, Anders & Tidemann, Jorg (ed.) (2019). Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing. Linköping University Electronic Press.  ISBN 978-91-7929-999-6.  66 s.
• Oepen, Stephan (ed.) (2017). Proceedings of the 2017 Shared Task on Extrinsic Parser Evaluation at the Fourth International Conference on Dependency Linguistics and the 15th International Conference on Parsing Technologies. Association for Computational Linguistics.  ISBN 978-1-945626-74-6.  99 s.

View all works in Cristin

• Øvrelid, Lilja (2019). Forskjeller mellom talemål og skrift. Hva kan trebanker fortelle oss?.
• Dahl, Fredrik Andreas; Kasicheyanula, Taraka Rama; Hurlen, Petter; Brekke, Pål Haugar; Husby, Haldor; Gundersen, Tore; Nytrø, Øystein & Øvrelid, Lilja (2019). Classifying Norwegian radiology reports with deep learning.
• Touileb, Samia; Pedersen, Truls Andre & Sjøvaag, Helle (2018). Automatically identifying names of unrecognized politicians.
• Sjøvaag, Helle; Pedersen, Truls Andre & Touileb, Samia (2018). Operationalising Diversity for Big Data Policy Research.
• Lison, Pierre (2016). Hybrid dialogue management + dialogue modelling for MT.
• Lison, Pierre (2016). A short introduction to statistical machine translation. Show summary

  Machine translation (MT) systems such as Google Translate have become part of our daily life. But how do they work? In this talk, I'll explain how these systems are built. In the first part of my talk, I'll present a general overview of the field and the key ideas driving modern MT systems. In the second part, I'll dig deeper into the statistical techniques used to estimate translation models from data, and discuss some of the current hot topics in the field.

• Lison, Pierre (2016). OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles. Show summary

  We present a new major release of the OpenSubtitles collection of parallel corpora. The release is compiled from a large database of movie and TV subtitles and includes a total of 1689 bitexts spanning 2.6 billion sentences across 60 languages. The release also incorporates a number of enhancements in the preprocessing and alignment of the subtitles, such as the automatic correction of OCR errors and the use of meta-data to estimate the quality of each subtitle and score subtitle pairs.

• Lapponi, Emanuele; Oepen, Stephan; Skjærholt, Arne & Velldal, Erik (2015). LAP: The CLARINO Language Analysis Portal.
• Fares, Murhaf; Oepen, Stephan & Velldal, Erik (2015). Identifying Compounds: On The Role of Syntax.

View all works in Cristin