Universal Morpho-Syntactic Parsing and the Contribution of Lexica: Analyzing the ONLP Lab Submission to the CoNLL 2018 Shared Task

What it is about

The ONLP Lab submission used UDPipe for segmentation and morphological disambiguation, then yap's arc-eager dependency parser (a Zhang–Nivre variant with morphological-signature features). It parsed 81 UD v2 test treebanks with an average LAS of 58.35, ranked 22nd. Low-resource languages got a model from a related treebank or from English EWT. The post-task study on Modern Hebrew (dev set) is the core: UDPipe's full pipeline reached 61.95 LAS and yap's dependency parser on UDPipe output 59.19. yap's own morphology with a data-driven analyzer dropped to 52.25. Swapping in the broad-coverage HebLex analyzer restored 60.94, and forcing the gold analysis into the lattice gave 71.39. With gold morphology the parser reached 79.33. The authors conclude that most Hebrew parsing errors come from missing lexical analyses, not from the parser, and they propose the CoNLL-UL format for sharing lexica.

Ideas

• I1. Make the lexicon the measured variable: a ladder of runs on a Hebrew dev set, each step with a single change (no lexicon, lexicon, lexicon plus forced gold path, gold morphology). The paper's numbers are the reference shape for the tools/hbo ladder. Run every step twice before reporting.
• I2. A CoNLL-UL-style export of the tools/hbo tables (lex, pre) with one row per analysis (form, lemma, UPOS, features), so that other parsers can read the same lattice and the lexicon can be shared.
• I3. For Mova's low-resource varieties (languages/arc-x-targum/, languages/jpa/), keep a small table of which trained model stands in for which variety, as the paper does with cs pud: cs pdt, and record every stand-in in the docs.

For Mova

I1 is a measurement for tools/hbo and is recorded in 13. Biblical Hebrew in Mova: the tools. I2 goes into tools/hbo and tools/macula dict, and the lexicon-coverage findings go into 12. Mova and Modern Hebrew: where it stands, what it would need. I3 goes into languages/arc-x-targum/ and languages/jpa/ as a note on the stand-in models.

Topics: Dependency parsing · Treebanks

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/k18-2021

@inproceedings{seker2018universal,
  title = {{Universal Morpho-Syntactic Parsing and the Contribution of Lexica: Analyzing the ONLP Lab Submission to the CoNLL 2018 Shared Task}},
  author = {Seker, Amit and More, Amir and Tsarfaty, Reut},
  booktitle = {Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies},
  year = {2018},
  doi = {10.18653/v1/k18-2021},
  url = {https://doi.org/10.18653/v1/k18-2021}
}

References

26 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. ## Acknowledgements Meni Adler and Michael Elhadad. 2006. An unsupervised morpheme-based hmm for hebrew morphological disambiguation. In Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Stroudsburg, PA, USA, ACL-44, pages 665–672. https://doi.org/10.3115/1220175.1220259. ↗ our card
2. We thank the CoNLL Shared Task Organizing Committee for their hard work and their timely support. We also thank the TIRA platform team (Potthast et al., 2014) for providing a system that facilitates competition and reproducible research. The research towards this shared task submission has been supported by the European Research Council, ERC-StG-2015 Grant 677352, and by an Israel Science Foundation (ISF) Grant 1739/26, for which we are grateful. find
3. Daniel Andor, Chris Alberti, David Weiss, Aliaksei Severyn, Alessandro Presta, Kuzman Ganchev, Slav Petrov, and Michael Collins. 2016. Globally normalized transition-based neural networks. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, August 7-12, 2016, Berlin, Germany, Volume 1: Long Papers. 1231.pdf. http://aclweb.org/anthology/P/P16/P16- ↗
4. Bernd Bohnet and Joakim Nivre. 2012. A transition-based system for joint part-of-speech tagging and labeled non-projective dependency parsing. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics, Stroudsburg, PA, USA, EMNLP-CoNLL ’12, pages 1455–1465. http://dl.acm.org/citation.cfm?id=2390948.2391114. ↗
5. Bernd Bohnet, Joakim Nivre, Igor Boguslavsky, Richárd Farkas, Filip Ginter, and Jan Hajic. 2013. Joint morphological and syntactic analysis for richly inflected languages. TACL 1:415–428. http://dblp.uni-trier.de/db/journals/tacl/tacl1.html. ↗
6. Amir More and Reut Tsarfaty. 2016. Data-driven morphological analysis and disambiguation for morphologically rich languages and universal dependencies. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. find
7. The COLING 2016 Organizing Committee, Osaka, Japan, pages 337–348. http://aclweb.org/anthology/C16-1033. ↗
8. Joakim Nivre, Željko Agić, Lars Ahrenberg, et al. 2017. Universal dependencies 2.0 CoNLL 2017 shared task development and test data. LIN-DAT/CLARIN digital library at the Institute of Formal and Applied Linguistics, Charles University. http://hdl.handle.net/11234/1-2184. ↗
9. Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Yoav Goldberg, Jan Hajič, Christopher Manning, Ryan McDonald, Slav Petrov, Sampo Pyysalo, Natalia Silveira, Reut Tsarfaty, and Daniel Zeman. 2016. Universal Dependencies v1: A multilingual treebank collection. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016). European Language Resources Association, Portoro, Slovenia, pages 1659– 1666. find our card
10. Sabine Buchholz and Erwin Marsi. 2006. CoNLL-X shared task on multilingual dependency parsing. In Proceedings of CoNLL-X. pages 149–164. find our card
11. Michael Collins and Brian Roark. 2004. Incremental parsing with the perceptron algorithm. In Proceedings of the 42Nd Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, Stroudsburg, PA, USA, ACL ’04. https://doi.org/10.3115/1218955.1218970. ↗ our card
12. Joakim Nivre, Johan Hall, Sandra Kübler, Ryan Mc-Donald, Jens Nilsson, Sebastian Riedel, and Deniz Yuret. 2007. find
13. The CoNLL 2007 shared task on dependency parsing. In Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007. pages 915–932. find
14. Sandra Kübler, Ryan McDonald, and Joakim Nivre. 2009. Dependency Parsing. Number 2 in Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers. find
15. Zhenghua Li, Min Zhang, Wanxiang Che, Ting Liu, and Wenliang Chen. 2014. Joint optimization for chinese POS tagging and dependency parsing. IEEE/ACM Trans. Audio, Speech & Language Processing 22(1):274–286. https://doi.org/10.1109/TASLP.2013.2288081. ↗
16. Zhenghua Li, Min Zhang, Wanxiang Che, Ting Liu, Wenliang Chen, and Haizhou Li. 2011. Joint models for chinese pos tagging and dependency parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Stroudsburg, PA, USA, EMNLP ’11, pages 1180–1191. http://dl.acm.org/citation.cfm?id=2145432.2145557. ↗
17. Amir More, Özlem Çetinoglu, Çagri Çöltekin, Nizar Habash, Benoı̂t Sagot, Djamé Seddah, Dima Taji, and Reut Tsarfaty. 2018. Conll-ul: Universal morphological lattices for universal dependency parsing. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018, Miyazaki, Japan, May 7-12, 2018.. find
18. Martin Potthast, Tim Gollub, Francisco Rangel, Paolo Rosso, Efstathios Stamatatos, and Benno Stein. 2014. Improving the reproducibility of PAN’s shared tasks: Plagiarism detection, author identification, and author profiling. In Evangelos Kanoulas, Mihai Lupu, Paul Clough, Mark Sander-son, Mark Hall, Allan Hanbury, and Elaine Toms, editors, Information Access Evaluation meets Multilinguality, Multimodality, and Visualization. 5th International Conference of the CLEF Initiative (CLEF 14). Springer, Berlin Heidelberg New York, pages 268–299. https://doi.org/10.1007/978-3-319-11382-1 22. ↗
19. Djamé Seddah, Sandra Kübler, and Reut Tsarfaty. 2014. Introducing the spmrl 2014 shared task on parsing morphologically-rich languages. pages 103–109. find
20. Djame Seddah, Reut Tsarfaty, Sandra Kübler, Marie Candito, D. Jinho Choi, Richárd Farkas, Jennifer Foster, Iakes Goenaga, Koldo Gojenola Gal-letebeitia, Yoav Goldberg, Spence Green, Nizar Habash, Marco Kuhlmann, Wolfgang Maier, Joakim Nivre, Adam Przepiórkowski, Ryan Roth, Wolfgang Seeker, Yannick Versley, Veronika Vincze, Marcin Woliński, Alina Wróblewska, and Villemonte Eric de la Clergerie. 2013. Proceedings of the fourth workshop on statistical parsing of morphologically-rich languages. Associa-Amir More, Amit Seker, Victoria Basmova, and Reut Tsarfaty. In Press. Joint transition-based models for morpho-syntactic parsing: Parsing strategies for mrls and a case study from modern hebrew. In Transactions of ACL. tion for Computational Linguistics, pages 146–182. http://aclweb.org/anthology/W13-4917. ↗ our card
21. Milan Straka, Jan Hajič, and Jana Straková. 2016. UD-Pipe: trainable pipeline for processing CoNLL-U files performing tokenization, morphological analysis, POS tagging and parsing. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016). European Language Resources Association, Portoro, Slovenia. find
22. Reut Tsarfaty and Yoav Goldberg. 2008. Word-based or morpheme-based? annotation strategies for modern Hebrew clitics. In Proceedings of LREC. find our card
23. Daniel Zeman, Jan Hajič, Martin Popel, Martin Potthast, Milan Straka, Filip Ginter, Joakim Nivre, and Slav Petrov. 2018. CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics, Brussels, Belgium, pages 1–20. find our card
24. Meishan Zhang, Yue Zhang, Wanxiang Che, and Ting Liu. 2014. Character-level chinese dependency parsing. In In Proceedings of the ACL. find
25. Yue Zhang and Stephen Clark. 2011. Syntactic processing using the generalized perceptron and beam search. Computational Linguistics 37(1):105–151. https://doi.org/10.1162/coli a 00037. ↗
26. Yue Zhang and Joakim Nivre. 2011. Transition-based dependency parsing with rich non-local features. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Short Papers - Volume 2. Association for Computational Linguistics, Stroudsburg, PA, USA, HLT ’11, pages 188–193. http://dl.acm.org/citation.cfm?id=2002736.2002777. ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/ud-2018-seker-universal-morpho-syntactic-parsing-contribution/