Neural Lemmatization of Multiword Expressions

What it is about

A multiword expression (MWE) such as "cartes bleues" must keep the agreement of its parts when it is lemmatized: the lemma is "carte bleue", not "carte bleu". The authors lemmatize MWEs word by word. An encoder reads the characters of each word and the word sequence of the MWE, and an attention decoder generates the part of the lemma for each word. The task is not disambiguation, because one MWE form almost always has one lemma. The model is evaluated on Italian, French, Polish and Portuguese, with a focus on French and Polish, and it generalizes to unknown MWEs. In the ablation on French, the recurrent layer over the word sequence is described as crucial, and the knowledge of simple-word lemmas adds 7 to 8 points.

Ideas

• I1. en/src/lexgen.rs: lemmatize English MWEs (phrasal verbs, compound nouns) part by part, with each word's lemma from the in-code dictionary and the agreement rule of the MWE as a table. Measure the MWE-level accuracy on the EWT test MWEs, and the share of MWEs whose lemma is wrong in the current lexicon.
• I2. Run the paper's ablation as a table in Mova: remove the simple-word lemma knowledge, then the POS tags, then the position, and print the accuracy for each removal on EWT test.
• I3. Use the paper's MWE-level and word-level accuracy as two numbers in en morph-eval, so one wrong word inside a correct MWE is visible.

For Mova

The code is en/src/lexgen.rs and en/src/morph.rs, with en morph-eval and en lexicon. The chapter is 19. The lexicon: vocabulary, multiword expressions and register. The paper has no English data and uses a neural model, so take the per-word method and the ablation plan only. Measure first on EWT test: MWE accuracy for the rule table, twice, against the held-out MWEs.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/w19-5117

@inproceedings{schmitt2019neural,
  title = {{Neural Lemmatization of Multiword Expressions}},
  author = {Schmitt, Marine and Constant, Mathieu},
  booktitle = {Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)},
  year = {2019},
  doi = {10.18653/v1/w19-5117},
  url = {https://doi.org/10.18653/v1/w19-5117}
}

References

34 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Georgiana Dinu Grzegorz Chrupala and Josef van Genabith. 2008. Learning morphology with morfette. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco. European Language Resources Association (ELRA). find our card
2. Anne Abeillé, Lionel Clément, and François Toussenel. 2003. Building a treebank for French. In Anne Abeillé, editor, Treebanks. Kluwer, Dordrecht. find
3. ATILF. 2016. Morphalou. ORTOLANG (Open Resources and TOols for LANGuage) –www.ortolang.fr. find
4. Michał Marcińczuk. 2017. Lemmatization of multiword common noun phrases and named entities in polish. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 483–491. INCOMA Ltd. find
5. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. CoRR, abs/1409.0473. find
6. Timothy Baldwin and Su Nam Kim. 2010. Multiword Expressions. In Nitin Indurkhya and Fred J. Damerau, editors, Handbook of Natural Language Processing, 2 edition, pages 267–292. CRC Press, Taylor and Francis Group, Boca Raton, FL, USA. find
7. Thomas Müller, Ryan Cotterell, Alexander Fraser, and Hinrich Schütze. 2015. Joint lemmatization and morphological tagging with lemming. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 2268– 2274, Lisbon, Portugal. Association for Computational Lingu… find
8. Toms Bergmanis and Sharon Goldwater. 2018. Context sensitive neural lemmatization with lematus. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1391–1400, New Orleans, Lou… find
9. Marcelo C.M. Muniz, Maria V. Nunes das Graas, and Eric Laporte. 2005. Unitex-pb, a set of flexible language resources for brazilian portuguese. In Proceedings of the Workshop on Technology on Information and Human Language (TIL), pages 2059– 2068. find
10. Kemal Oflazer, Özlem Çetinoğlu, and Bilge Say. 2004. Integrating morphology with multi-word expression processing in turkish. In Second ACL Workshop on Multiword Expressions: Integrating Processing, pages 64–71, Barcelona, Spain. Association for Computational Linguistics. find
11. Bartosz Broda, Michal Marcinczuk, Marek Maziarz, Adam Radziszewski, and Adam Wardynski. 2012. Kpwr: Towards a free corpus of polish. In Proceedings of the Eighth International Conference on Language Resources and Evaluation, LREC 2012, Istanbul, Turkey, May 23-25, 2012, pages 3218–3222. find
12. Kemal Oflazer and Ilker Kuruoz. 1994. Tagging and morphological disambiguation of turkish text. In Proceedings of the Fourth Conference on Applied Natural Language Processing, pages 144–149, Stuttgart, Germany. Association for Computational Linguistics. find
13. Marie Candito, Mathieu Constant, Carlos Ramisch, Agata Savary, Yannick Parmentier, Caroline Pasquer, and Jean-Yves Antoine. 2017. Annotation d’expressions polylexicales verbales en français. In 24e conférence sur le Traitement Automatique des Langues Naturelles (TALN), Actes de TALN, volume 2 : ar… find
14. Caroline Pasquer, Agata Savary, Carlos Ramisch, and Jean-Yves Antoine. 2018. If you’ve seen some, you’ve seen them all: Identifying variants of multiword expressions. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2582–2594. Association for Computational Ling… find
15. Mathieu Constant, Glen Eryiit, Johanna Monti, Lonneke van der Plas, Carlos Ramisch, Michael Rosner, and Amalia Todirascu. 2017. Multiword expression processing: A survey. Computational Linguistics, 43(4):837–892. find
16. Paumier, Nakamura, and Voyatzi. 2009. Unitex, a corpus processing system with multi-lingual linguistic resources. In eLexicography in the 21st century: new challenges, new applications (eLEX’09), pages 173–175. find
17. Filip Gralinski, Agata Savary, Monika Czerepowicka, and Filip Makowiecki. 2010. Computational lexicography of multi-word units. how efficient can it be? In Proceedings of the 2010 Workshop on Multiword Expressions: from Theory to Applications, pages 2–10, Beijing, China. find
18. Coling 2010 Organizing Committee. find
19. Jakub Piskorski, Marcin Sydow, and Anna Kup. 2007. Lemmatization of Polish Person Names. In ACL 2007. Proceedings of the Workshop on Balto-Slavonic NLP 2007, pages 27–34. Association for Computational Linguistics. find
20. Maurice Gross. 1986. Lexicon grammar. the representation of compound words. In Proceedings of the 11th International Conference on Computational Linguistics, COLING ’86, Bonn, Germany, August 25-29, 1986, pages 1–6. find
21. Adam Radziszewski. 2013. Learning to lemmatise polish noun phrases. In Proceedings of the 51st Annual shared task: A cross-framework evaluation of parsing morphologically rich languages. In Proceedings of the Fourth Workshop on Statistical Parsing of Morphologically-Rich Languages, pages 146–182, Se… find
22. Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 701–709, Sofia, Bulgaria. Association for Computational Linguistics. find
23. Carlos Ramisch, Silvio Ricardo Cordeiro, Agata Savary, Veronika Vincze, Verginica Barbu Mititelu, Archna Bhatia, Maja Buljan, Marie Candito, Polona Gantar, Voula Giouli, Tunga Gngr, Abdelati Hawwari, Uxoa Iurrieta, Jolanta Kovalevskait, Simon Krek, Timm Lichte, Chaya Liebeskind, Johanna Monti, Carla… find
24. Max D. Silberztein. 1994. Intex: A corpus processing system. In Proceedings of the 15th Conference on Computational Linguistics - Volume 1, Proceedings of the 15th International Conference on Computational Linguistics (COLING 1994), pages 579– 583, Stroudsburg, PA, USA. Association for Computational… find
25. Ranka Stankovic, Cvetana Krstev, Ivan Obradovic, Biljana Lazic, and Aleksandra Trtovac. 2016. Rule-based automatic multi-word term extraction and lemmatization. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Paris, France. European Language Res… find
26. Elisabete Ranchhod, Cristina Mota, and Jorge Baptista. 1999. A computational lexicon of portuguese for automatic text parsing. In Proceedings of SIGLEX’99: Standardizing Lexical Resources, 37th Annual Meeting of the ACL, pages 74–81. find
27. Milan Straka and Jana Straková. 2017. Tokenizing, pos tagging, lemmatizing and parsing ud 2.0 with udpipe. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 88–99, Vancouver, Canada. Association for Computational Linguistics. find our card
28. Ivan A. Sag, Timothy Baldwin, Francis Bond, Ann Copestake, and Dan Flickinger. 2002. Multiword Expressions: A Pain in the Neck for NLP. In Alexander Gelbukh, editor, Computational Linguistics and Intelligent Text Processing, volume 2276 of Lecture Notes in Computer Science, pages 1–15. Springer Berl… find our card
29. S. Vietri and A. Elia. 2000. Electronic dictionaries and linguistic analysis of italian large corpora. In JADT 2000 - Actes des 5es Journees internationales d’Analyse statistique des Donnes Textuelles. find
30. Agata Savary, Bartosz Zaborowski, Aleksandra Krawczyk-Wieczorek, and Filip Makowiecki. 2012. Sejfek - a lexicon and a shallow grammar of polish economic multi-word units. In Proceedings of the 3rd Workshop on Cognitive Aspects of the Lexicon, pages 195–214, Mumbai, India. find
31. The COLING 2012 Organizing Committee. find
32. Carsten Schnober, Steffen Eger, Erik-Lân Do Dinh, and Iryna Gurevych. 2016. Still not there? comparing traditional sequence-to-sequence models to encoder-decoder neural networks on monotone string translation tasks. In Proceedings of COLING 2016, the 26th International Conference on Computational L… find
33. The COLING 2016 Organizing Committee. find
34. Djamé Seddah, Reut Tsarfaty, Sandra Kübler, Marie Candito, Jinho D. Choi, Richárd Farkas, Jennifer Foster, Iakes Goenaga, Koldo Gojenola Galletebeitia, Yoav Goldberg, Spence Green, Nizar Habash, Marco Kuhlmann, Wolfgang Maier, Joakim Nivre, Adam Przepiórkowski, Ryan Roth, Wolfgang Seeker, Yannic… find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/lingbulk-2019-schmitt-neural-lemmatization-multiword-expressions/