Academic Interests
- Natural Language Processing
- Artificial Intelligence
- Machine Learning
- Computational Linguistics
- Machine Translation
- Semantics for Natural Languages
- Logic
Teaching
Programs:
Courses:
Previous courses
Higher education and employment history
- Professor, Dept. of Informatics, UiO, 2006-
- Professor, Dept. of Linguistics, UiO, 1994-2005
- Ass. Professor, Dept. of Linguistics and Philosophy, 1989-1994
- Dr. philos, Dept. of Mathematics, UiO, 1989
- Studies in Mathematics, Philosophy, Informatics, Psychology
Publications
-
Nooralahzadeh, Farhad; Lønning, Jan Tore & Øvrelid, Lilja
(2019).
Reinforcement-based denoising of distantly supervised NER with partial annotation,
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019).
Association for Computational Linguistics (ACL).
ISSN 9781950737789.
p. 225–234.
doi:
10.18653/v1/D19-6125.
Full text in Research Archive
Show summary
Existing named entity recognition (NER) systems rely on large amounts of human-labeled data for supervision. However, obtaining large-scale annotated data is challenging particularly in specific domains like health-care, e-commerce and so on. Given the availability of domain specific knowledge resources, (e.g., ontologies, dictionaries), distant supervision is a solution to generate automatically labeled training data to reduce human effort. The outcome of distant supervision for NER, however, is often noisy. False positive and false negative instances are the main issues that reduce performance on this kind of auto-generated data. In this paper, we explore distant supervision in a supervised setup. We adopt a technique of partial annotation to address false negative cases and implement a reinforcement learning strategy with a neural network policy to identify false positive instances. Our results establish a new state-of-the-art on four benchmark datasets taken from different domains and different languages. We then go on to show that our model reduces the amount of manually annotated data required to perform NER in a new domain.
-
Nooralahzadeh, Farhad; Øvrelid, Lilja & Lønning, Jan Tore
(2018).
Evaluation of Domain-specific Word Embeddings using Knowledge Resources.
In Calzolari, Nicoletta; Choukri, Khalid; Cieri, Christopher; Declerck, Thierry; Goggi, Sara; Hasida, Koiti; Isahara, Hitoshi; Maegaard, Bente; Mariani, Joseph; Mazo, Hélène; Moreno, Asuncion; Odijk, Jan; Piperidis, Stelios & Tokunaga, Takenobu (Ed.),
Proceedings of the Eleventh International Conference on Language Resources and Evaluation.
European Language Resources Association.
ISSN 9791095546009.
p. 1438–1445.
Full text in Research Archive
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.
-
-
Jørgensen, Fredrik & Lønning, Jan Tore
(2009).
A Minimal Recursion Semantic Analysis of Locatives.
Computational Linguistics.
ISSN 0891-2017.
35(2),
p. 229–270.
Full text in Research Archive
-
Oepen, Stephan; Velldal, Erik; Lønning, Jan Tore; Meurer, Paul; Rosén, Victoria & Flickinger, Dan
(2007).
Towards Hybrid Quality-Oriented Machine Translation. On Linguistics and Probabilities in MT.
In Way, Andy & Gawronska, Barbara (Ed.),
Proceedings of the 11th International Conference on Theoretical Issues in Machine Translation.
Skövde University Studies in Informatics.
ISSN 9789197709507.
p. 144–153.
Full text in Research Archive
-
-
-
Lønning, Jan Tore
(2006).
Language technology and the science of linguistics.
In Solstad, Torgrim; Grønn, Atle & Haug, Dag Trygve Truslew (Ed.),
A Festschrift for Kjell Johan Sæbø: In Partial Fulfilment of the Requirements for the Celebration of his 50th Birthday.
Forfatterne.
ISSN 9788299728904.
p. 107–119.
Full text in Research Archive
Show summary
The festschrift contains contributions from the following authors: Bergljot Behrens, Reinhard Blutner, Pål Kristian Eriksen, Cathrine Fabricius-Hansen, Jens Erik Fenstad, Atle Grønn, Janne Bondi Johannessen, Sveta Krasikova, Jan Tore Lønning, Doris Penka, Wiebke Ramm, Torgrim Solstad, Arnim von Stechow, Ingebjørg Tonne, Eirik Welo, Henk Zeevat and Thomas Ede Zimmermann
-
-
Lønning, Jan Tore
(1997).
Plurals and Collectivity.
In Benthem, Johan van & Meulen, Alice G. B. ter (Ed.),
Handbook of Logic and Language.
Elsevier Science B.V., Amsterdam.
ISSN 9780444817143.
p. 1009–1053.
Full text in Research Archive
View all works in NVA
-
-
Oepen, Stephan; Dyvik, Helge; Flickinger, Daniel Paul; Lønning, Jan Tore; Meurer, Paul & Rosén, Victoria
(2005).
Holistic regression testing for high-quality MT. Some methodological and technological reflections.
Full text in Research Archive
-
-
-
-
-
-
-
-
View all works in NVA
Published
Nov. 4, 2010 2:07 PM
- Last modified
Jan. 2, 2025 1:18 PM
