Research

My research is within the field of computational linguistics, where I have worked on word alignment, annotation transfer, machine translation, language modeling, computational typology, language asssement and learning, and more.

During 2016 I was a postdoc at the University of Helsinki and what was then the Department of Modern Languages, but since January 2017 I am (back) at the Department of Linguistics, Stockholm University.

You can find most of my recent projects on my Github page, and some other academic projects can be found at the website of the NLP group (maybe, if anybody has updated it this decade). In particular, you may be interested in the following tools and datasets:

List of publications

This is a list work-related publications I have (co-)authored. I try to keep it as complete and up-to-date as possible. Automatically created lists tend to be inaccurate since they have trouble telling me from the other Robert Östling at Stockholm University.

Kurfali, M. and Östling, R. (2023). A distantly supervised grammatical error detection/correction system for Swedish. In Proceedings of the 12th Workshop on NLP for Computer Assisted Language Learning, pages 35--39, Tórshavn, Faroe Islands. LiU Electronic Press. [ bib | http ]

Östling, R. and Kurfalı, M. (2023). Language Embeddings Sometimes Contain Typological Generalizations. Computational Linguistics, 49(4):1003--1051, https://direct.mit.edu/coli/article-pdf/49/4/1003/2269496/coli_a_00491.pdf. [ bib | DOI | arXiv | http ]

Östling, R., Gillholm, K., Kurfalı, M., Mattson, M., and Wirén, M. (2023). Evaluation of really good grammatical error correction. 2308.08982. Accepted to LREC-COLING 2024. Preprint at https://arxiv.org/abs/2308.08982. [ bib | arXiv ]

Östling, R. (2022). Mot en mänskligare maskinöversättning. In Volodina, E., Dannélls, D., Berdicevskis, A., Forsberg, M., and Virk, S., editors, LIVE and LEARN -- Festschrift in honor of Lars Borin, pages 171--173. [ bib | http ]

Tyrefors, B., Ahlström, L., Enbågen, I., Rydell, M., and Östling, R. (2022). En modell för att mäta och belöna progression inom sfi (SOU 2022:17). [ bib | http ]

Kurfali, M. and Östling, R. (2021b). Probing multilingual language models for discourse. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 8--19, Online. Association for Computational Linguistics. [ bib | DOI | http ]

Kurfali, M. and Östling, R. (2021a). Let's be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction. In Proceedings of the 1st Workshop on Understanding Implicit and Underspecified Language, pages 1--10, Online. Association for Computational Linguistics. [ bib | DOI | http ]

Kurfali, M., Östling, R., Sjons, J., and Wirén, M. (2020). A multi-word expression dataset for swedish. In Proceedings of the Twelfth International Conference on Language Resources and Evaluation (LREC 2020), Marseille, France. European Languages Resources Association (ELRA). [ bib ]

Kurfali, M. and Östling, R. (2020). Disambiguation of potentially idiomatic expressions with contextual embeddings. In Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons (MWE-LEX 2020), COLING 2020. [ bib ]

Andersson, M., Kurfali, M., and Östling, R. (2020). A sentiment-annotated dataset of english causal connectives. In Proceedings of the 14th Linguistic Annotation Workshop (LAW), COLING 2020. [ bib ]

Kurfali, M. and Östling, R. (2019b). Zero-shot transfer for implicit discourse relation classification. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 226--231, Stockholm, Sweden. Association for Computational Linguistics. [ bib | DOI | http ]

Kurfali, M. and Östling, R. (2019a). Noisy parallel corpus filtering through projected word embeddings. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pages 277--281, Florence, Italy. Association for Computational Linguistics. [ bib | http ]

Bjerva, J., Östling, R., Han Veiga, M., Tiedemann, J., and Augenstein, I. (2019). What do language representations really represent? Computational Linguistics, 45(2):381--389, https://doi.org/10.1162/COLI_a_00351. [ bib | DOI | arXiv | www: ]

Ek, A., Wirén, M., Östling, R., N. Björkenstam, K., Grigonytė, G., and Gustafson Capková, S. (2018). Identifying speakers and addressees in dialogues extracted from literary fiction. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Languages Resources Association (ELRA). [ bib | http ]

Östling, R., Börstell, C., and Courtaux, S. (2018). Visual iconicity across sign languages: Large-scale automated video analysis of iconic articulators and locations. Frontiers in Psychology, 9:1--17. Article 725. [ bib | DOI | http ]

Östling, R. (2018). Part of speech tagging: Shallow or deep learning? North European Journal of Language Technology, (5):1--15. [ bib | DOI | http ]

Östling, R. and Grigonyte, G. (2017). Transparent text quality assessment with convolutional neural networks. In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications, pages 282--286, Copenhagen, Denmark. Association for Computational Linguistics. [ bib | http ]

Bjerva, J., Grigonyte, G., Östling, R., and Plank, B. (2017). Neural networks and spelling features for native language identification. In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications, pages 235--239, Copenhagen, Denmark. Association for Computational Linguistics. [ bib | http ]

Östling, R., Scherrer, Y., Tiedemann, J., Tang, G., and Nieminen, T. (2017b). The Helsinki neural machine translation system. In Proceedings of the Second Conference on Machine Translation, pages 338--347, Copenhagen, Denmark. Association for Computational Linguistics. [ bib | http ]

Östling, R., Börstell, C., Gärdenfors, M., and Wirén, M. (2017a). Universal dependencies for swedish sign language. In Proceedings of the 21st Nordic Conference on Computational Linguistics, pages 303--308, Gothenburg, Sweden. Association for Computational Linguistics. [ bib | http ]

Börstell, C. and Östling, R. (2017). Iconic locations in swedish sign language: Mapping form to meaning with lexical databases. In Proceedings of the 21st Nordic Conference on Computational Linguistics, pages 221--225, Gothenburg, Sweden. Association for Computational Linguistics. [ bib | http ]

Bjerva, J. and Östling, R. (2017). Cross-lingual learning of semantic textual similarity with multilingual word representations. In Proceedings of the 21st Nordic Conference on Computational Linguistics, pages 211--215, Gothenburg, Sweden. Association for Computational Linguistics. [ bib | http ]

Östling, R. and Tiedemann, J. (2017). Continuous multilinguality with language vectors. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 644--649, Valencia, Spain. Association for Computational Linguistics. [ bib | http ]

Wirén, M., N. Björkenstam, K., and Östling, R. (2017). Modelling the informativeness of non-verbal cues in parent–child interaction. In Proceedings of Interspeech 2017, Interspeech, pages 2203--2207. [ bib | DOI ]

Östling, R. and Bjerva, J. (2017). Su-rug at the conll-sigmorphon 2017 shared task: Morphological inflection with attentional sequence-to-sequence models. In Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection, pages 110--113. Association for Computational Linguistics. [ bib | DOI | http ]

Tjong Kim Sang, E., Bollmann, M., Boschker, R., Casacuberta, F., Dietz, F., Dipper, S., Domingo, M., van der Goot, R., van Koppen, M., Ljubešić, N., Östling, R., Petran, F., Pettersson, E., Scherrer, Y., Schraagen, M., Sevens, L., Tiedemann, J., Vanallemeersch, T., and Zervanou, K. (2017). The clin27 shared task: Translating historical text to contemporary language for improving automatic linguistic annotation. Computational Linguistics in the Netherlands Journal, 7:53--64. [ bib ]

Östling, R. (2016a). A Bayesian model for joint word alignment and part-of-speech transfer. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 620--629, Osaka, Japan. [ bib | .pdf ]

Östling, R. and Tiedemann, J. (2016). Efficient word alignment with Markov Chain Monte Carlo. Prague Bulletin of Mathematical Linguistics, 106:125--146. [ bib | .pdf ]

Tiedemann, J., Cap, F., Kanerva, J., Ginter, F., Stymne, S., Östling, R., and Weller-Di Marco, M. (2016). Phrase-based SMT for Finnish with more data, better models and alternative alignment and translation tools. In Proceedings of the First Conference on Machine Translation, pages 391--398, Berlin, Germany. Association for Computational Linguistics. [ bib | http ]

Björkenstam, K. N., Wirén, M., and Östling, R. (2016). Modelling the informativeness and timing of non-verbal cues in parent-child interaction. In Proceedings of the 7th Workshop on Cognitive Aspects of Computational Language Learning, pages 82--90, Berlin. Association for Computational Linguistics. [ bib | .pdf ]

Östling, R. (2016c). Morphological reinflection with convolutional neural networks. In Proceedings of the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 23--26, Berlin, Germany. Association for Computational Linguistics. [ bib | DOI | http ]

Börstell, C., Hörberg, T., and Östling, R. (2016). Distribution and duration of signs and parts of speech in Swedish Sign Language. Sign Language & Linguistics, 19(2):143--196. [ bib ]

Börstell, C. and Östling, R. (2016). Visualizing lects in a sign language corpus: Mining lexical variation data in lects of Swedish sign language. In Proceedings of the 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining, pages 13--18. [ bib | .pdf ]

Östling, R. (2016b). The Lexical Typology of Semantic Shifts, chapter Studying colexification through massively parallell corpora, pages 157--176. De Gruyter. [ bib | DOI | http ]

Östling, R. (2015c). Word order typology through multilingual word alignment. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 205--211, Beijing, China. Association for Computational Linguistics. [ bib | http ]

Berggren, M., Karlgren, J., Östling, R., and Parkvall, M. (2015). Inferring the location of authors from words in their texts. In Proceedings of the 20th Nordic Conference on Computational Linguistics (NODALIDA 2015), volume 23 of NEALT Proceedings Series, pages 211--218, Vilnius, Lithuania. [ bib | .pdf ]

Östling, R., Börstell, C., and Wallin, L. (2015). Enriching the Swedish Sign Language Corpus with part of speech tags using joint Bayesian word alignment and annotation transfer. In Proceedings of the 20th Nordic Conference on Computational Linguistics (NODALIDA 2015), volume 23 of NEALT Proceedings Series, pages 263--268, Vilnius, Lithuania. [ bib | .pdf ]

Östling, R. (2015a). Bayesian Models for Multilingual Word Alignment. PhD thesis, Stockholm University. ISBN 978-91-7649-151-5. [ bib | http ]

Östling, R. (2015b). Svenska dialektkartor på sekunden. Språkbruk, 3:10--13. [ bib ]

Östling, R. (2014). Bayesian word alignment for massively parallel texts. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers, pages 123--127, Gothenburg, Sweden. Association for Computational Linguistics. [ bib | http ]

Östling, R., Smolentzov, A., Tyrefors Hinnerich, B., and Höglin, E. (2013). Automated essay scoring for Swedish. In Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Applications, pages 42--47, Atlanta, Georgia. Association for Computational Linguistics. [ bib | http ]

Loftsson, H. and Östling, R. (2013). Tagging a morphologically complex language using an averaged perceptron tagger: The case of Icelandic. In Proceedings of the 19th Nordic Conference on Computational Linguistics (NODALIDA 2013), NEALT Proceedings Series, pages 105--119, Oslo, Norway. [ bib | .pdf ]

Östling, R. and Wirén, M. (2013). Compounding in a Swedish blog corpus. In López, L. A., Brylla, C. S., and Shaw, P., editors, Computer mediated discourse across languages, volume New Series 12 of Stockholm Studies in Modern Philology, pages 45--63. Stockholm University. [ bib | http ]

Östling, R. (2013). Stagger: An open-source part of speech tagger for Swedish. North European Journal of Language Technology, 3:1--18. [ bib | http ]

Östling, R. (2012). Stagger: A modern POS tagger for Swedish. In Proceedings of The Fourth Swedish Language Technology Conference, pages 83--84, Lund, Sweden. [ bib | http ]

Östling, R. (2010). A construction grammar method for disambiguating Swedish compounds. In SLTC 2010 Workshop on Compounds and Multiword Expressions. [ bib | http ]

Östling, R. and Knutsson, O. (2009). A corpus-based tool for helping writers with Swedish collocations. In Proceedings of the Workshop on Extracting and Using Constructions in NLP, volume T2009 of SICS Technical Report, pages 28--33, Odense, Denmark. ISSN 1100-3154. [ bib | .pdf ]

Östling, R. (2009). A corpus-based collocation assistant for Swedish text. Master's thesis, Royal Institute of Technology (KTH). [ bib | .pdf ]


This file was generated by bibtex2html 1.99.


Home |About me |Chinese |Research |Software |Electronics |Radio