Universal Joint Morph-Syntactic Processing: The Open University of Israel's Submission to The CoNLL 2017 Shared Task

What it is about

The OpenU-NLP-Lab system for the CoNLL 2017 UD shared task is a transition-based, non-neural joint morphological disambiguator and arc-standard dependency parser (built in yap). It takes a lattice of morphological analyses per token, produced by a data-driven analyzer that learns its lexicon from the UD training data, and picks one analysis per token while parsing. It parsed all 81 UD v2 test treebanks with a macro-average LAS of 56.56, using only the training sets. For Modern Hebrew, swapping in the lexicon-backed HEBLEX analyzer raised word-segmentation F1 from 81.26 to 87.48, a 33% cut in error rate. The authors also report two bugs: SPMRL-style clitic suffix features confused the disambiguator, and some large treebanks could not be serialized (model over 2^30 bytes), so only their parser was trained there.

Ideas

• I1. Split the errors by source: for each wrong segmentation on a Hebrew dev set, check whether the gold analysis is in the candidate list at all. The paper's gap between the realistic and the "infused" (gold path forced into the lattice) runs is a diagnostic to copy into tools/hbo.
• I2. Keep the two Hebrew conventions apart: SPMRL marks some clitics as suffix features, UD splits them into syntactic words. The paper's fix was an extra flag on clitic-bearing words. A similar flag in the tools/hbo segmenter, with a test that the same token gets the same split under both conventions.
• I3. Lexicon as an input: the paper's central claim is that a UD-compatible lexicon (CoNLL-UL) matters more than the parser for Hebrew. Measure whether a lattice built from the tools/hbo lex table beats a data-driven one on unpointed text, with two identical runs before any claim.

For Mova

I1 and I2 are tests for tools/hbo (segmenter output and its evaluation). I3 is a measurement for the lex table of tools/hbo, relevant to 1. Script and pointing (unpointed reading) and 12. Mova and Modern Hebrew: where it stands, what it would need, the plan for a Modern Hebrew reader.

Topics: Dependency parsing · Treebanks

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/k17-3027

@inproceedings{more2017universal,
  title = {{Universal Joint Morph-Syntactic Processing: The Open University of Israel's Submission to The CoNLL 2017 Shared Task}},
  author = {More, Amir and Tsarfaty, Reut},
  booktitle = {Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies},
  year = {2017},
  doi = {10.18653/v1/k17-3027},
  url = {https://doi.org/10.18653/v1/k17-3027}
}

References

25 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. 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
2. The COLING 2016 Organizing Committee, Osaka, Japan, pages 337–348. http://aclweb.org/anthology/C16-1033. ↗
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. http://aclweb.org/anthology/P/P16/P16-1231.pdf. ↗
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. 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
7. Joakim Nivre, Željko Agić, Lars Ahrenberg, et al. 2017a. 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. ↗
8. 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
9. Joakim Nivre, Johan Hall, Sandra Kübler, Ryan Mc-Donald, Jens Nilsson, Sebastian Riedel, and Deniz Yuret. 2007. find
10. The CoNLL 2007 shared task on dependency parsing. In Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007. pages 915–932. find
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 et al. 2017b. Universal Dependencies 2.0. LINDAT/CLARIN digital library at the Institute of Formal and Applied Linguistics, Charles University, Prague, http://hdl.handle.net/ 11234/1-1983. http://hdl.handle.net/11234/1-1983. ↗
13. Yoav Goldberg and Joakim Nivre. 2012. A dynamic oracle for arc-eager dependency parsing. In COLING 2012, 24th International Conference on Computational Linguistics, Proceedings of the Conference: Technical Papers, 8-15 December 2012, Mumbai, India. pages 959–976. http://aclweb.org/anthology/C/C12/C12-1059.pdf. ↗
14. 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. ↗
15. Sandra Kübler, Ryan McDonald, and Joakim Nivre. 2009. Dependency Parsing. Number 2 in Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers. find
16. 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. ↗
17. 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. ↗
18. Djamé Seddah, Sandra Kübler, and Reut Tsarfaty. 2014. Introducing the spmrl 2014 shared task on parsing morphologically-rich languages. pages 103–109. find
19. 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. Association for Computational Linguistics, pages 146–182. http://aclweb.org/anthology/W13-4917. ↗
20. 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
21. Reut Tsarfaty and Yoav Goldberg. 2008. Word-based or morpheme-based? annotation strategies for modern Hebrew clitics. In Proceedings of LREC. find our card
22. Daniel Zeman, Martin Popel, Milan Straka, Jan Hajič, Joakim Nivre, Filip Ginter, Juhani Luotolahti, Sampo Pyysalo, Slav Petrov, Martin Potthast, Francis Tyers, Elena Badmaeva, Memduh Gökırmak, Anna Nedoluzhko, Silvie Cinková, Jan Hajič jr., Jaroslava Hlaváčová, Václava Kettnerová, Zdeňka Urešová, Jenna Kanerva, Stina Ojala, Anna Missilä, Christopher Manning, Sebastian Schuster, Siva Reddy, Dima Taji, Nizar Habash, Herman Leung, Marie-Catherine de Marneffe, Manuela Sanguinetti, Maria Simi, Hiroshi Kanayama, Valeria de Paiva, Kira Droganova, Hěctor Martı́nez Alonso, Hans Uszkoreit, Vivien Macketanz, Aljoscha Burchardt, Kim Harris, Katrin Marheinecke, Georg Rehm, Tolga Kayadelen, Mohammed Attia, Ali Elkahky, Zhuoran Yu, Emily Pitler, Saran Lertpradit, Michael Mandl, Jesse Kirchner, Hector Fernandez Alcalde, Jana Strnadova, Esha Banerjee, Ruli Manurung, Antonio Stella, Atsuko Shimada, Sookyoung Kwak, Gustavo Mendonça, Tatiana Lando, Rattima Nitisaroj, and Josie Li. 2017. CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
23. Meishan Zhang, Yue Zhang, Wanxiang Che, and Ting Liu. 2014. Character-level chinese dependency parsing. In In Proceedings of the ACL. find
24. 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. ↗
25. 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-2017-more-universal-joint-morph-syntactic-processing/