Parsing Gapping Constructions Based on Grammatical and Semantic Roles

What it is about

A gapping construction, as in "John ate bread, and Mary ate rice", elides the repeated verb in the second conjunct. To recover the elided material, the parser must find which words in the gapped conjunct correspond to which words in the full one. The method works on Penn Treebank constituency trees in which the grammatical and semantic role tags (subject, temporal, locative and so on) are kept, and it marks the gapped conjunct with a GAP tag. The correspondence is found by a dynamic-programming sequence alignment, modified from Needleman–Wunsch so that it respects order and non-overlap, and the match score requires the same role. On the test section (section 23), the alignment F-score is 12.9 for the earlier method of Kummerfeld and Klein, 31.6 with the new method without BERT, 70.8 with BERT, and 89.3 with gold tags. The tag annotation has only a tiny cost on constituency parsing (F 95.77 against 95.64 with BERT).

Ideas

I1. prag/src/frames.rs and en/src/parse.rs: after a UD parse, align the remnant words of a gapped conjunct to the correlate words by a dynamic programme, using the relation labels (nsubj, obj, obl:tmp) as the role match. Recover the missing verb and report how many elided predicates are recovered on a hand-labelled set.
I2. Keep the two structural constraints as hard rules: order-preserving and non-overlapping alignments. Measure the gain of each constraint on its own by ablation.
I3. Report precision and recall separately. The paper's gain comes mostly from recall, and a recovery rule that adds false material must be visible.

For Mova

The chapter is 29. Ellipsis, word order and information structure, with 24. Coordination and subordination for the coordinated structure. The code is prag/src/frames.rs (where the recovered predicate would fill a frame) and en/src/parse.rs for the UD trees. The measures: recovery F on a hand-labelled gapping set, the constraint ablation, and the precision and recall pair, all run twice. The BERT part is not an idea for Mova; the alignment and the role match are.

Topics: Semantic role labeling

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.emnlp-main.218

@inproceedings{kato2020parsing,
  title = {{Parsing Gapping Constructions Based on Grammatical and Semantic Roles}},
  author = {Kato, Yoshihide and Matsubara, Shigeki},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2020},
  doi = {10.18653/v1/2020.emnlp-main.218},
  url = {https://doi.org/10.18653/v1/2020.emnlp-main.218}
}

References

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

Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. ↗
Jessica Ficler and Yoav Goldberg. 2016. Improved parsing for argument-clusters coordination. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 72–76, Berlin, Germany. Association for Computational Linguistics. find
Ryan Gabbard, Seth Kulick, and Mitchell Marcus. 2006. Fully parsing the Penn Treebank. In Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, pages 184– 191, New York City, USA. Association for Computational Linguistics. find our card
Nikita Kitaev, Steven Cao, and Dan Klein. 2019. Multilingual constituency parsing with self-attention and pre-training. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3499–3505, Florence, Italy. Association for Computational Linguistics. find
Nikita Kitaev and Dan Klein. 2018. Constituency parsing with a self-attentive encoder. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2676–2686, Melbourne, Australia. Association for Computational Linguistics. find
Jonathan K. Kummerfeld and Dan Klein. 2017. Parsing with traces: An O(n 4 ) algorithm and a structural representation. Transactions of the Association for Computational Linguistics, 5:441–454. find
Mitchell P. Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English: the Penn Treebank. Computational Linguistics, 19(2):310–330. find our card
Saul B. Needleman and Christian D. Wunsch. 1970. A general method applicable to the search for similarities in the amino acid sequence of two proteins. Journal of molecular biology, 48(3):443–453. Joakim Nivre, Željko Agić, Lars Ahrenberg, Lene Antonsen, Maria Jesus Aranzabe, Masayuki Asahara, Luma Ateyah, Mohammed Attia, Aitziber Atutxa, Liesbeth Augustinus, Elena Badmaeva, Miguel Ballesteros, Esha Banerjee, Sebastian Bank, Verginica Barbu Mititelu, John Bauer, Kepa Bengoetxea, Riyaz Ahmad Bhat, Eckhard Bick, Victoria Bobicev, Carl Börstell, Cristina Bosco, Gosse Bouma, Sam Bowman, Aljoscha Burchardt, Marie Candito, Gauthier Caron, Gülşen Cebiroğlu Eryiğit, Giuseppe G. A. Celano, Savas Cetin, Fabricio Chalub, Jinho Choi, Silvie Cinková, Çağrı Çöltekin, Miriam Connor, Elizabeth Davidson, Marie-Catherine de Marneffe, Valeria de Paiva, Arantza Diaz de Ilarraza, Peter Dirix, Kaja Dobrovoljc, Timothy Dozat, Kira Droganova, Puneet Dwivedi, Marhaba Eli, Ali Elkahky, Tomaž Erjavec, Richárd Farkas, Hector Fernandez Alcalde, Jennifer Foster, Cláudia Freitas, Katarína Gajdošová, Daniel Galbraith, Marcos Garcia, Moa Gärdenfors, Kim Gerdes, Filip Ginter, Iakes Goenaga, Koldo Gojenola, Memduh Gökırmak, Yoav Goldberg, Xavier Gómez Guinovart, Berta Gonzáles Saavedra, Matias Grioni, Normunds Grūzı̄tis, Bruno Guillaume, Nizar Habash, Jan Hajič, Jan Hajič jr., Linh Hà Mỹ, Kim Harris, Dag Haug, Barbora Hladká, Jaroslava Hlaváčová, Florinel Hociung, Petter Hohle, Radu Ion, Elena Irimia, Tomáš Jelínek, Anders Johannsen, Fredrik Jørgensen, Hüner Kaşıkara, Hiroshi Kanayama, Jenna Kanerva, Tolga Kayadelen, Václava Kettnerová, Jesse Kirchner, Natalia Kotsyba, Simon Krek, Veronika Laippala, Lorenzo Lambertino, Tatiana Lando, John Lee, Phương Lê Hồng, Alessandro Lenci, Saran Lertpradit, Herman Leung, Cheuk Ying Li, Josie Li, Keying Li, Nikola Ljubešić, Olga Loginova, Olga Lyashevskaya, Teresa Lynn, Vivien Macketanz, Aibek Makazhanov, Michael Mandl, Christopher Manning, Cătălina Mărănduc, David Mareček, Katrin Marheinecke, Héctor Martínez Alonso, André Martins, Jan Mašek, Yuji Matsumoto, Ryan McDonald, Gustavo Mendonça, Niko Miekka, Anna Missilä, Cătălin Mititelu, Yusuke Miyao, Simonetta Montemagni, Amir More, Laura Moreno Romero, Shinsuke Mori, Bohdan Moskalevskyi, Kadri Muischnek, Kaili Müürisep, Pinkey Nainwani, Anna Nedoluzhko, Gunta Nešpore-Bērzkalne, Lương Nguyễn Thi., Huyền Nguyễn Thi. Minh, Vitaly Nikolaev, Hanna Nurmi, Stina Ojala, Petya Osenova, Robert Östling, Lilja Øvrelid, Elena Pascual, Marco Passarotti, Cenel-Augusto Perez, Guy Perrier, Slav Petrov, Jussi Piitulainen, Emily Pitler, Barbara Plank, Martin Popel, Lauma Pretkalnin , a, Prokopis Prokopidis, Tiina Puolakainen, Sampo Pyysalo, Alexandre Rademaker, Loganathan Ramasamy, Taraka Rama, Vinit Ravishankar, Livy Real, Siva Reddy, Georg Rehm, Larissa Rinaldi, Laura Rituma, Mykhailo Romanenko, Rudolf Rosa, Davide Rovati, Benoît Sagot, Shadi Saleh, Tanja Samardžić, Manuela Sanguinetti, Baiba Saulı̄te, Sebastian Schuster, Djamé Seddah, Wolfgang Seeker, Mojgan Seraji, Mo Shen, Atsuko Shimada, Dmitry Sichinava, Natalia Silveira, Maria Simi, Radu Simionescu, Katalin Simkó, Mária Šimková, Kiril Simov, Aaron Smith, Antonio Stella, Milan Straka, Jana Strnadová, Alane Suhr, Umut Sulubacak, Zsolt Szántó, Dima Taji, Takaaki Tanaka, Trond Trosterud, Anna Trukhina, Reut Tsarfaty, Francis Tyers, Sumire Uematsu, Zdeňka Urešová, Larraitz Uria, Hans Uszkoreit, Sowmya Vajjala, Daniel van Niekerk, Gertjan van Noord, Viktor Varga, Eric Villemonte de la Clergerie, Veronika Vincze, Lars Wallin, Jonathan North Washington, Mats Wirén, Tak-sum Wong, Zhuoran Yu, Zdeněk Žabokrtský, Amir Zeldes, Daniel Zeman, and Hanzhi Zhu. 2017. Universal dependencies LINDAT/CLARIAH-CZ digital library at 2.1. the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University. and reconstructing elided predicates. 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 1156–1168, New Orleans, Louisiana. Association for Computational Linguistics. find
Wolfgang Seeker, Richárd Farkas, Bernd Bohnet, Helmut Schmid, and Jonas Kuhn. 2012. Data-driven dependency parsing with empty heads. In Proceedings of COLING 2012: Posters, pages 1081–1090, Mumbai, India. find
The COLING 2012 Organizing Committee. find
Maria Ponomareva, Kira Droganova, Ivan Smurov, and Tatiana Shavrina. 2019. AGRR 2019: Corpus for gapping resolution in Russian. In Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing, pages 35–43, Florence, Italy. Association for Computational Linguistics. find
Sebastian Schuster and Christopher D. Manning. 2016. Enhanced English Universal Dependencies: An improved representation for natural language understanding tasks. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 2371–2378, Portorož, Slovenia. European Language Resources Association (ELRA). find our card
Sebastian Schuster, Joakim Nivre, and Christopher D. Manning. 2018. Sentences with gapping: Parsing find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/kato-2020-parsing-gapping-constructions-based-grammatical/