Mova0.5 pre-release⌕
☰
home / docs / papers / English / CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

What it is about

The shared task asks systems to parse raw text, with no gold tokenization, sentence splitting or tags, into UD trees for 49 languages. Training data came from UD 2.0 (64 treebanks), and test data was hidden until the end: 55 large treebanks, 8 small ones, 14 new parallel PUD sets and 4 "surprise" languages with almost no training data. The main metric is macro-averaged LAS F1 over 81 test files, with punctuation counted and tokens aligned to gold. The Stanford team won with a macro LAS of 76.30; the UDPipe 1.1 baseline scored 68.35, and only 12 of 32 systems beat it. Surprise languages stayed mostly below 50% LAS, and the authors report that a language-detection fallback in one system silently cost it about ten LAS points, which shows how easily evaluation can hide failures.

Ideas

For Mova

Touches languages/en/07-punctuation-capitals-numbers (tokenization) and 20-syntax-overview, and the en crate (tok.rs, ctx.rs, parse.rs, the en parse-eval command) and tools/parsecmp. Measure first the gap between gold-token and raw-text LAS on PUD English, and make the fallback check (I2) before any new number is claimed. The macro-average is a shared-task result, not a Mova target.

Topics: Universal Dependencies · Treebanks

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/k17-3001

@inproceedings{zeman2017conll,
  title = {{CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies}},
  author = {Zeman, Daniel and Popel, Martin and Straka, Milan and Hajič, Jan and Nivre, Joakim and Ginter, Filip and Luotolahti, Juhani and Pyysalo, Sampo and Petrov, Slav and Potthast, Martin and Tyers, Francis and Badmaeva, Elena and Gokirmak, Memduh and Nedoluzhko, Anna and Cinková, Silvie and jr and Hlaváčová, Jaroslava and Kettnerová, Václava and Urešová, Zdeňka and Kanerva, Jenna and Ojala, Stina and Missilä, Anna and Manning, Christopher D. and Schuster, Sebastian and Reddy, Siva and Taji, Dima and Habash, Nizar and Leung, Herman and Marneffe, Marie-Catherine de and Sanguinetti, Manuela and Simi, Maria and Kanayama, Hiroshi and Paiva, Valeria de and Droganova, Kira and Alonso, Héctor Martínez and Çöltekin, Çağrı and Sulubacak, Umut and Uszkoreit, Hans and Macketanz, Vivien and Burchardt, Aljoscha and Harris, Kim and Marheinecke, Katrin and Rehm, Georg and Kayadelen, Tolga and Attia, Mohammed and Elkahky, Ali and Yu, Zhuoran and Pitler, Emily and Lertpradit, Saran and Mandl, Michael and Kirchner, Jesse and Alcalde, Hector Fernandez and Strnadová, Jana and Banerjee, Esha and Manurung, Ruli and Stella, Antonio and Shimada, Atsuko and Kwak, Sookyoung and Mendonça, Gustavo and Lando, Tatiana and Nitisaroj, Rattima and Li, Josie},
  booktitle = {Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies},
  year = {2017},
  doi = {10.18653/v1/k17-3001},
  url = {https://doi.org/10.18653/v1/k17-3001}
}

References

40 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. We are grateful to all the contributors to Universal Dependencies; without their effort a task like this simply wouldn’t be possible. The work described herein, including data preparation for the CoNLL 2017 UD Shared Task, has been supported by the following grants and projects: “CRACKER,” H2020 Project No. 645357 of the European Commission; “MANYLA,” Grant No. GA15-10472S of the Grant Agency of the Czech Republic; FIN-Burak Kerim Akkuş, Heval Azizoğlu, and Ruket Çakıcı. 2017. Initial explorations of CCG supertagging for Universal Dependency parsing. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  2. Chris Alberti, Daniel Andor, Ivan Bogatyy, Michael Collins, Dan Gillick, Lingpeng Kong, Terry Koo, Ji Ma, Mark Omernick, Slav Petrov, Chayut Thanapirom, Zora Tung, and David Weiss. 2017. Syntaxnet models for the conll Abbreviation Segment B(ase) UDP O(wn) Morph None B(ase) UDP Own AG Aux Joint Parsing B(ase) Single Ensemble Suffixes Embed B(ase) C(rawl) Treebank O FB Random AddData None OPUS Wiki PTB CCG Surp Mono Canon Cross Suffixes Para Single All Explanation Word and sentence segmentation Baseline UDPipe Adapted/retrained UDPipe Own system for word and sentence segmentation Morphological analysis (including part-of-speech tags) No prediction of tags or morphological features Baseline UDPipe Adapted/retrained UDPipe Own system for predicting tags and/or morphological features Apertium/Giellatekno morphological analyzers Tags predicted as an auxiliary task during parser training Tags predicted jointly with parsing Parsing technique Baseline UDPipe Single parser Ensemble of several parsers G = Graph-based T = Transition-based R = Rule-based (with statistics or unsupervised learning) Word embeddings Pre-trained word embeddings provided by organizers Word embeddings trained on the crawled data provided by organizers Word embeddings trained (only) on the UD treebanks Word embeddings trained on data from OPUS Pre-trained embeddings released by Facebook Randomly initialized (trained only with parser) Additional data used (over and above treebanks + raw text) No additional data Parallel data from OPUS Wikipedia dumps Penn Treebank (sic) CCGBank (sic) Approach to surprise languages Monolingual parser trained on dev data Single canonical model for all surprise languages Cross-lingual parsing S = Single-source M = Multi-source D = Delexicalized Approach to parallel test sets Model trained on a single treebank from each language Model trained on all treebanks from each language *Table 12: Abbreviations used in Table 11.* 2017 shared task. CoRR abs/1703.04929. http://arxiv.org/abs/1703.04929. ↗
  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. Lauriane Aufrant and Guillaume Wisniewski. 2017. LIMSI@CoNLL’17: UD shared task. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  5. Anders Björkelund, Agnieszka Faleńska, Xiang Yu, and Jonas Kuhn. 2017. IMS at the CoNLL 2017 UD shared task: CRFs and perceptrons meet neural networks. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  6. Sabine Buchholz and Erwin Marsi. 2006. CoNLL-X shared task on multilingual dependency parsing. In Proceedings of the 10th Conference on Computational Natural Language Learning (CoNLL-X). Association for Computational Linguistics, pages 149– 164. http://anthology.aclweb.org/W/W06/W06-29.pdf#page=165. ↗ our card
  7. Wanxiang Che, Jiang Guo, Yuxuan Wang, Bo Zheng, Huaipeng Zhao, Yang Liu, and Ting Liu. 2017. The HIT-SCIR system for end-to-end parsing of 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
  8. Ayan Das, Zaffar Affan, and Sudeshna Sarkar. 2017. Delexicalized transfer parsing for low-resource languages using transformed and combined treebanks. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  9. Eric De La Clergerie, Benoı̂t Sagot, and Djamé Seddah. 2017. The ParisNLP entry at the CoNLL UD shared task 2017: A tale of a #parsingtragedy. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  10. Miryam de Lhoneux, Yan Shao, Ali Basirat, Eliyahu Kiperwasser, Sara Stymne, Yoav Goldberg, and Joakim Nivre. 2017. From raw text to Universal Dependencies - look, no tags! In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  11. Johannes Heinecke and Munshi Asadullah. 2017. Multi-model and crosslingual dependency analysis. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  12. Ryan Hornby, Clark Taylor, and Jungyeul Park. 2017. Corpus selection approaches for 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
  13. Tao Ji, Yuanbin Wu, and Man Lan. 2017. A fast and lightweight system for multilingual dependency parsing. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  14. Hiroshi Kanayama, Masayasu Muraoka, and Kat-Marie-Catherine de Marneffe and Christopher D. sumasa Yoshikawa. 2017. A semi-universal Manning. 2008. Stanford typed dependencies pipelined approach to the CoNLL 2017 UD shared manual. Technical report, Stanford University. http://nlp.stanford.edu/software/dependencies_manual.pdf. task. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Uni-Timothy Dozat, Peng Qi, and Christopher D. Manning. versal Dependencies. Association for Computational 2017. Stanford’s graph-based neural dependency Linguistics. parser at the CoNLL 2017 shared task. In Proceed-Jenna Kanerva, Juhani Luotolahti, and Filip Ginter. ings of the CoNLL 2017 Shared Task: Multilingual 2017. TurkuNLP: Delexicalized pre-training of Parsing from Raw Text to Universal Dependencies. word embeddings for dependency parsing. In Pro-Association for Computational Linguistics. ceedings of the CoNLL 2017 Shared Task: Multilin-Stefan Daniel Dumitrescu, Tiberiu Boroş, and Dan gual Parsing from Raw Text to Universal Dependen-Tufiş. 2017. RACAI’s natural language processing cies. Association for Computational Linguistics. pipeline for Universal Dependencies. In Proceed-Ömer Kırnap, Berkay Furkan Önder, and Deniz Yuret. ings of the CoNLL 2017 Shared Task: Multilingual 2017. Parsing with context embeddings. In Pro-Parsing from Raw Text to Universal Dependencies. ceedings of the CoNLL 2017 Shared Task: Multilin-Association for Computational Linguistics. gual Parsing from Raw Text to Universal Dependen-Marcos Garcia and Pablo Gamallo. 2017. A rule-based cies. Association for Computational Linguistics. system for cross-lingual parsing of Romance lan-Kyungtae Lim and Thierry Poibeau. 2017. A system guages with universal dependencies. In Proceedings for multilingual dependency parsing based on bidi-of the CoNLL 2017 Shared Task: Multilingual Pars-rectional LSTM feature representations. In Proceeding from Raw Text to Universal Dependencies. As-ings of the CoNLL 2017 Shared Task: Multilingual sociation for Computational Linguistics. Parsing from Raw Text to Universal Dependencies. Filip Ginter, Jan Hajič, Juhani Luotolahti, Milan Straka, Association for Computational Linguistics. and Daniel Zeman. 2017. CoNLL 2017 shared task -Ryan McDonald, Joakim Nivre, Yvonne Quirmbach-automatically annotated raw texts and word embed-Brundage, Yoav Goldberg, Dipanjan Das, Kuz-dings. LINDAT/CLARIN digital library at the In-man Ganchev, Keith Hall, Slav Petrov, Hao stitute of Formal and Applied Linguistics, Charles Zhang, Oscar Täckström, Claudia Bedini, Núria University. http://hdl.handle.net/11234/1-1989. ↗
  15. Bertomeu Castelló, and Jungmee Lee. 2013. find
  16. Univer-Nizar Y Habash. 2010. Introduction to Arabic natural sal dependency annotation for multilingual parsing. language processing, volume 3. Morgan & Claypool In Proceedings of the 51st Annual Meeting of the As-Publishers. sociation for Computational Linguistics. Sofia, Bulgaria. Allan Hanbury, Henning Müller, Krisztian Balog, Tor-Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S. ben Brodt, Gordon V. Cormack, Ivan Eggel, Tim Corrado, and Jeffrey Dean. 2013. Distributed Gollub, Frank Hopfgartner, Jayashree Kalpathy-representations of words and phrases and their com-Cramer, Noriko Kando, Anastasia Krithara, Jimmy positionality. In Advances in Neural Information Lin, Simon Mercer, and Martin Potthast. 2015. Processing Systems 26: 27th Annual Conference Evaluation-as-a-Service: Overview and Outlook. on Neural Information Processing Systems. pages ArXiv e-prints http://arxiv.org/abs/1512.07454.3111–3119. http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality. ↗
  17. Christophe Moor, Paola Merlo, James Henderson, and Haozhou Wang. 2017. Geneva DINN parser: a neural network dependency parser ten years later. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  18. Amir More and Reut Tsarfaty. 2017. Universal joint morph-syntactic processing: The Open University of Israel’s submission to the CoNLL 2017. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  19. Dat Quoc Nguyen, Mark Dras, and Mark Johnson. 2017. A novel neural network model for joint POS tagging and graph-based dependency parsing. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. Joakim Nivre, Željko Agić, Lars Ahrenberg, Lene Antonsen, Maria Jesus Aranzabe, Masayuki Asahara, Luma Ateyah, Mohammed Attia, Aitziber Atutxa, Elena Badmaeva, Miguel Ballesteros, Esha Banerjee, Sebastian Bank, John Bauer, Kepa Bengoetxea, Riyaz Ahmad Bhat, Eckhard Bick, Cristina Bosco, Gosse Bouma, Sam Bowman, Aljoscha Burchardt, Marie Candito, Gauthier Caron, Gülşen Ce-biroğlu Eryiğit, Giuseppe G. A. Celano, Savas Cetin, Fabricio Chalub, Jinho Choi, Yongseok Cho, Silvie Cinková, Çağrı Çöltekin, Miriam Connor, Marie-Catherine de Marneffe, Valeria de Paiva, Arantza Diaz de Ilarraza, Kaja Dobrovoljc, Timothy Dozat, Kira Droganova, Marhaba Eli, Ali Elkahky, Tomaž Erjavec, Richárd Farkas, Hector Fernandez Alcalde, Jennifer Foster, Cláudia Freitas, Katarína Gajdošová, Daniel Galbraith, Marcos Garcia, 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, Petter Hohle, Radu Ion, Elena Irimia, Anders Johannsen, Fredrik Jørgensen, Hüner Kaşıkara, Hiroshi Kanayama, Jenna Kanerva, Tolga Kayadelen, Václava Kettnerová, Jesse Kirchner, Natalia Kotsyba, Simon Krek, Sookyoung Kwak, Veronika Laippala, Lorenzo Lambertino, Tatiana Lando, Phương Lê Hồng, Alessandro Lenci, Saran Lertpradit, Herman Leung, Cheuk Ying Li, Josie Li, Nikola Ljubešić, Olga Loginova, Olga Lyashevskaya, Teresa Lynn, Vivien Macketanz, Aibek Makazhanov, Michael Mandl, Christopher Manning, Ruli Manurung, Cătălina Mărănduc, David Mareček, Katrin Marheinecke, Héctor Martínez Alonso, André Martins, Jan Mašek, Yuji Matsumoto, Ryan McDonald, Gustavo Mendonça, Anna Missilä, Verginica Mititelu, Yusuke Miyao, Simonetta Montemagni, Amir More, Laura Moreno Romero, Shunsuke Mori, Bohdan Moskalevskyi, Kadri Muischnek, Nina Mustafina, Kaili Müürisep, Pinkey Nainwani, Anna Nedoluzhko, Lương Nguyễn Thị, Huyền Nguyễn Thị Minh, Vitaly Nikolaev, Rattima Nitisaroj, Hanna Nurmi, Stina Ojala, Petya Osenova, Lilja Øvrelid, Elena Pascual, Marco Passarotti, Cenel-Augusto Perez, Guy Perrier, Slav Petrov, Jussi Piitulainen, Emily Pitler, Barbara Plank, Martin Popel, Lauma Pretkalniņa, Prokopis Prokopidis, Tiina Puolakainen, Sampo Pyysalo, Alexandre Rademaker, Livy Real, Siva Reddy, Georg Rehm, Larissa Rinaldi, Laura Rituma, Rudolf Rosa, Davide Rovati, Shadi Saleh, Manuela Sanguinetti, Baiba Saulı̄te, Yanin Sawanakunanon, Sebastian Schuster, Djamé Seddah, Wolfgang Seeker, Mojgan Seraji, Lena Shakurova, Mo Shen, Atsuko Shimada, Muh Shohibussirri, Natalia Silveira, Maria Simi, Radu Simionescu, Katalin Simkó, Mária Šimková, Kiril Simov, Aaron Smith, Antonio Stella, 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, Gertjan van Noord, Viktor Varga, Veronika Vincze, Jonathan North Washington, Zhuoran Yu, Zdeněk Žabokrtský, Daniel Zeman, and Hanzhi Zhu. 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. Joakim Nivre, Željko Agić, Lars Ahrenberg, Maria Jesus Aranzabe, Masayuki Asahara, Aitziber Atutxa, Miguel Ballesteros, John Bauer, Kepa Bengoetxea, Riyaz Ahmad Bhat, Eckhard Bick, Cristina Bosco, Gosse Bouma, Sam Bowman, Marie Candito, Gülşen Cebiroğlu Eryiğit, Giuseppe G. A. Celano, Fabricio Chalub, Jinho Choi, Çağrı Çöltekin, Miriam Connor, Elizabeth Davidson, Marie-Catherine de Marneffe, Valeria de Paiva, Arantza Diaz de Ilarraza, Kaja Dobrovoljc, Timothy Dozat, Kira Droganova, Puneet Dwivedi, Marhaba Eli, Tomaž Erjavec, Richárd Farkas, Jennifer Foster, Cláudia Freitas, Katarína Gajdošová, Daniel Galbraith, Marcos Garcia, 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, Linh Hà Mỹ, Dag Haug, Barbora Hladká, Petter Hohle, Radu Ion, Elena Irimia, Anders Johannsen, Fredrik Jørgensen, Hüner Kaşıkara, Hiroshi Kanayama, Jenna Kanerva, Natalia Kotsyba, Simon Krek, Veronika Laippala, Phương Lê Hồng, Alessandro Lenci, Nikola Ljubešić, Olga Lyashevskaya, Teresa Lynn, Aibek Makazhanov, Christopher Manning, Cătălina Mărănduc, David Mareček, Héctor Martínez Alonso, André Martins, Jan Mašek, Yuji Matsumoto, Ryan McDonald, Anna Missilä, Verginica Mititelu, Yusuke Miyao, Simonetta Montemagni, Amir More, Shunsuke Mori, Bohdan Moskalevskyi, Kadri Muischnek, Nina Mustafina, Kaili Müürisep, Lương Nguyễn Thị, Huyền Nguyễn Thị Minh, Vitaly Nikolaev, Hanna Nurmi, Stina Ojala, Petya Osenova, Lilja Øvrelid, Elena Pascual, Marco Passarotti, Cenel-Augusto Perez, Guy Perrier, Slav Petrov, Jussi Piitulainen, Barbara Plank, Martin Popel, Lauma Pretkalniņa, Prokopis Prokopidis, Tiina Puolakainen, Sampo Pyysalo, Alexandre Rademaker, Loganathan Ramasamy, Livy Real, Laura Rituma, Rudolf Rosa, Shadi Saleh, Manuela Sanguinetti, Baiba Saulı̄te, Sebastian Schuster, Djamé Seddah, Wolfgang Seeker, Mojgan Seraji, Lena Shakurova, Mo Shen, Dmitry Sichinava, Natalia Silveira, Maria Simi, Radu Simionescu, Katalin Simkó, Mária Šimková, Kiril Simov, Aaron Smith, Alane Suhr, Umut Sulubacak, Zsolt Szántó, Dima Taji, Takaaki Tanaka, Reut Tsarfaty, Francis Tyers, Sumire Uematsu, Larraitz Uria, Gertjan van Noord, Viktor Varga, Veronika Vincze, Jonathan North Washington, Zdeněk Žabokrtský, Amir Zeldes, Daniel Zeman, and Hanzhi Zhu. 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. ↗ our card
  20. 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, Portorož, Slovenia, pages 1659–1666. find our card
  21. Joakim Nivre and Chiao-Ting Fang. 2017. Universal dependency evaluation. In Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017). pages 86–95. find
  22. Joakim Nivre, Johan Hall, Sandra Kübler, Ryan McDonald, Jens Nilsson, Sebastian Riedel, and Deniz Yuret. 2007. find
  23. The CoNLL 2007 shared task on dependency parsing. In Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007. Association for Computational Linguistics, pages 915–932. http://www.aclweb.org/anthology/D/D07/D07-1.pdf#page=949. ↗
  24. Slav Petrov, Dipanjan Das, and Ryan T. McDonald. 2011. A universal part-of-speech tagset. CoRR abs/1104.2086. http://arxiv.org/abs/1104.2086. ↗
  25. Slav Petrov and Ryan McDonald. 2012. Overview of the 2012 shared task on parsing the web. In Proceedings of the First Workshop on Syntactic Analysis of Non-Canonical Language (SANCL). Montréal, Canada. http://www.petrovi.de/data/sancl12.pdf. ↗
  26. Martin Popel, Zdeněk Žabokrtský, and Martin Vojtek. 2017. Udapi: Universal API for universal dependencies. In NoDaLiDa 2017 Workshop on Universal Dependencies. Göteborgs universitet, Göteborg, Sweden, pages 96– 101. http://aclweb.org/anthology/W/W17/W17-0412.pdf. ↗ our card
  27. 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. ↗
  28. Xian Qian and Yang Liu. 2017. A non-DNN feature engineering approach to dependency parsing – FBAML at CoNLL 2017 shared task. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  29. Motoki Sato, Hitoshi Manabe, Hiroshi Noji, and Yuji Matsumoto. 2017. Adversarial training for cross-domain universal dependency parsing. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  30. Djamé Seddah, Sandra Kübler, and Reut Tsarfaty. 2014. Introducing the SPMRL 2014 shared task on parsing morphologically-rich languages. In First Joint Workshop on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical Languages. Dublin, Ireland, pages 103–109. http://www.aclweb.org/anthology/W14-6111. ↗
  31. Djamé Seddah, Reut Tsarfaty, Sandra Kübler, Marie Candito, Jinho D. Choi, Richárd Farkas, Jennifer Foster, Iakes Goenaga, Koldo Gojenola, 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 Eric Villemonte de la Clérg-erie. 2013. Overview of the SPMRL 2013 shared task: Cross-framework evaluation of parsing morphologically rich languages. In Proceedings of the Fourth Workshop on Statistical Parsing of Morphologically Rich Languages. Association for Computational Linguistics, Seattle, Washington, USA, pages 146–182. http://www.aclweb.org/anthology/W13-4917. ↗
  32. Tianze Shi, Felix G. Wu, Xilun Chen, and Yao Cheng. 2017. Combining global models for parsing 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
  33. Milan Straka. 2017. CoNLL 2017 shared task - UD-Pipe baseline models and supplementary materials. LINDAT/CLARIN digital library at the Institute of Formal and Applied Linguistics, Charles University. http://hdl.handle.net/11234/1-1990. ↗
  34. 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, Portorož, Slovenia. find
  35. 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. Association for Computational Linguistics. find our card
  36. Jörg Tiedemann. 2012. Parallel data, tools and interfaces in OPUS. In Nicoletta Calzolari (Conference Chair), Khalid Choukri, Thierry Declerck, Mehmet Ugur Dogan, Bente Maegaard, Joseph Mariani, Jan Odijk, and Stelios Piperidis, editors, Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC’12). European Language Resources Association (ELRA), Istanbul, Turkey. find
  37. Clara Vania, Xingxing Zhang, and Adam Lopez. 2017. UParse: the Edinburgh system for the CoNLL 2017 UD shared task. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  38. David Vilares and Carlos Gómez-Rodríguez. 2017. A non-projective greedy dependency parser with bidirectional LSTMs. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  39. Hao Wang, Hai Zhao, and Zhisong Zhang. 2017. A transition-based system for universal dependency parsing. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card
  40. Kuan Yu, Pavel Sofroniev, and Erik Schill. 2017. The parse is darc and full of errors: Universal dependency parsing with transition-based and graph-based algorithms. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics. find our card

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/ud-2017-zeman-conll-2017-shared-task-multilingual/