ITU

Natural Language Processing

Organisational unit: Research Group

IT University of Copenhagen
Rued Langgaards Vej 7
DK-2300 Copenhagen S
Denmark

Contact information

Research Group Coordinator

Leon Derczynski (leod@itu.dk)

Organisation profile

ITU NLP researches in natural language processing, with extra focus on deep learning approaches, NLP for Danish, information extraction, parsing, summarization, bias reduction, fake news detection, social media processing, and low-resource languages.


Machine understanding of natural language is a major AI challenge of our time. ITU's Natural Language Processing Group adresses this challenge in all core areas of Natural Language Processing including:

• Dependency parsing. When understanding a sentence, we need to know who did what to whom – i.e., how the words relate to each other. Parsing is a process for understanding these relations. In dependency parsing, a sentence’s syntactic structure is described using the sentence’s words and a set of relations that connect the words. ITU NLP works on building parsing tools and improving parsing practices.

• Social media. Although there’s a lot of unimportant-seeming noise and chatter on social media, it’s actually very useful – not just for targeting politics and business strategy, but also for detecting virus outbreaks and earthquakes. The highly varied language on social media is difficult to process. We focus on techniques for processing this language and ways of using social media intelligence.

• Multilingual NLP. Lots of research is done on English – but there are approximately 7000 known living languages, separated over 128 language family groups. So it’s very important to get the state of the art to work in more languages than English. As well as covering many others, ITU NLP includes special focus on the Danish languages.

• Stance detection & fake news analysis. We can estimate how true or false an online claim is by measuring the reaction around it – the stance people take to it. At ITU NLP we continue work on veracity in digital media.

• Entity detection. Finding where people, organizations and places are mentioned in text is really important for many tasks – building automatic summaries, doing business intelligence, and so on. These names are called entities, which can include things like names of drugs, genes, products, and so on. Finding these names well is tough, and a theme of research at ITU NLP.

• Deep learning approaches. Language is tough to process, and so at ITU we use modern deep learning techniques to address this huge AI challenge. We’re interested in multi-task learning, transfer learning, efficient nets, and working with new and powerful toolkits, and have a selection of GPU resources for our research computing.

• Representation learning. It’s difficult to map the language of humans, with words, to the language of computers, with numbers. Finding a way of representing words using numbers can be done automatically, which is called representation learning. At ITU we’re particularly interested in learning multilingual representations, learning representations across different domains (a domain is a specific type of language, like news articles, conversation, doctor’s notes and so on), and distributional clustering.

  1. 2019
  2. Published

    At a Glance: The Impact of Gaze Aggregation Views on Syntactic Tagging

    Klerke, S. & Plank, B., 2019, The First Workshop Beyond Vision and LANguage: inTEgrating Real-World kNowledge : EMNLP-IJCNLP Workshop. Hong Kong: Association for Computational Linguistics, p. 51–61

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

  3. Published

    Bornholmsk Natural Language Processing: Resources and Tools

    Derczynski, L. & Kjeldsen, A. S., 2019, Proceedings of the Nordic Conference of Computational Linguistics (2019). Linköping University Electronic Press, p. 338–344 (NEALT (Northern European Association of Language Technology) Proceedings Series).

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

  4. Published

    Joint Rumour Stance and Veracity Prediction

    Edelbo Lillie, A., Middelboe, E. R. & Derczynski, L., 2019, Nordic Conference of Computational Linguistics (2019). Linköping University Electronic Press, p. 208–221 (NEALT (Northern European Association of Language Technology) Proceedings Series).

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

  5. Published

    Lexical Resources for Low-Resource PoS Tagging in Neural Times

    Plank, B. & Klerke, S., 2019, Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19) . Association for Computational Linguistics, p. 25–34 (NEALT (Northern European Association of Language Technology) Proceedings Series).

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

  6. Published

    Measuring Catastrophic Forgetting in Visual Question Answering

    Greco, C., Plank, B., Fernandez, R. & Bernardi, R., 2019, Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS) 2019.

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsCommunication

  7. Published

    MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding

    Rethmeier, N. & Plank, B., 2019, Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)): RepL4NLP-2019. Florence: Association for Computational Linguistics, p. 49-54

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

  8. Published

    Normalisation of imprecise temporal expressions extracted from text

    Tissot, H., Roberts, A., Derczynski, L. & Didonet Del Fabro, M., 2019, In : Knowledge and Information Systems. p. 1-34

    Research output: Journal Article or Conference Article in JournalJournal articleResearchpeer-review

  9. Published

    Offensive Language and Hate Speech Detection for Danish

    Derczynski, L., 2019.

    Research output: Contribution to conference - NOT published in proceeding or journalPaperResearch

  10. Published

    Political Stance in Danish

    Lehmann, R. & Derczynski, L., 2019, Proceedings of the Nordic Conference of Computational Linguistics (2019). Linköping University Electronic Press, p. 197–207 (NEALT (Northern European Association of Language Technology) Proceedings Series).

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

  11. Published

    Recurrent models and lower bounds for projective syntactic decoding

    Schluter, N., 2019, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Vol. Volume 1 (Long and Short Papers). p. 251-260 10 p.

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review