Elamur Research⌕
☰
home / papers / 2021 / The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task

The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task

Summary

The paper describes the DCU-EPFL system submitted to the IWPT 2021 shared task. The goal of the task is to build Enhanced Universal Dependencies (EUD) graphs directly from raw text. Such graphs extend ordinary UD trees: a word can have several heads, and the graph can contain empty nodes and cycles. As a result, they are closer to the semantic structure of the sentence. The system was evaluated on 29 treebanks for 17 languages. The pipeline consists of three parts. Stanza splits the text into sentences and tokens and performs morphosyntactic tagging. XLM-R provides contextual word vectors. A separate module scores each "head — dependent" pair and selects a label for the edge. Finally, a script repairs the graphs so that every node is reachable from the root. In the official ranking, the system placed 6th out of 9 (coarse ELAS 83.57). After the deadline, the authors replaced Stanza with Trankit and switched to XLM-R Large. They also concatenated treebanks and added joint training with a basic-tree parser, which raised the result to 88.04. The work shows that a simple multilingual approach can come close to the leaders. In addition, the basic tree proved to be a useful cue for EUD, in particular for Ukrainian.

Key points

  • Edges are scored following the Kiperwasser & Goldberg scheme: the head and dependent vectors are combined and fed into an MLP, after which a sigmoid with a threshold of 0.5 is applied. This scheme outperformed biaffine attention, and the authors take this as a sign that EUD is close to semantic parsing.
  • Tamil had the least training data. When English EWT and GUM were added to it, ELAS increased by more than 12 points, i.e., the number of errors decreased by roughly 24% in relative terms.
  • The multi-task model combines the EUD parser with the Dozat & Manning biaffine parser, and the losses of both are weighted equally. For languages without treebank concatenation, it improved the result everywhere, most of all for Arabic, French and Ukrainian. Combined with concatenation, it helped only some of the languages: for Czech and English, concatenation alone worked better, and for Polish, joint training brought no gain.
  • The best unofficial run (+Concat+MTL) achieves an ELAS of 88.04. Among the official systems, it would have ranked second for 13 of the 17 languages and first for Italian and Russian. For comparison, the organizers' baseline, which simply copies the gold tree, scores 79.87.
  • The code is open: github.com/jbrry/IWPT-2021-shared-task.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Dependency parsing · Treebanks

Cited by

1 paper of our library cites it (of the 140673 whose bibliographies we read); each has a page here.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.iwpt-1.22 · arXiv 2107.01982

@inproceedings{barry2021dcu,
  title = {{The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task}},
  author = {Barry, James and Mohammadshahi, Alireza and Wagner, Joachim and Foster, Jennifer and Henderson, James},
  booktitle = {Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)},
  year = {2021},
  doi = {10.18653/v1/2021.iwpt-1.22},
  eprint = {2107.01982},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2021.iwpt-1.22}
}

References

30 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. James Barry, Joachim Wagner, and Jennifer Foster. 2020. The ADAPT enhanced dependency parser at the IWPT 2020 shared task. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 227–235, Online.… find our card
  2. Gosse Bouma, Djamé Seddah, and Daniel Zeman. 2020. Overview of the IWPT 2020 shared task on parsing into enhanced Universal Dependencies. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages… find our card
  3. Gosse Bouma, Djamé Seddah, and Daniel Zeman. 2021. From raw text to enhanced universal dependencies: The parsing shared task at iwpt 2021. In Proceedings of the 17th International Conference on Parsing Technologies (IWPT 2021), pages 146–157, Bangkok, Thailand (online). Association for Computationa… find our card
  4. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association f… find
  5. Mathieu Dehouck, Mark Anderson, and Carlos Gómez-Rodrı́guez. 2020. Efficient EUD parsing. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 192–205, Online. Association for Computational L… find
  6. 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,… find
  7. Timothy Dozat and Christopher D. Manning. 2016. Deep biaffine attention for neural dependency parsing. CoRR, abs/1611.01734. find our card
  8. Timothy Dozat and Christopher D. Manning. 2018. Simpler but more accurate semantic dependency parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 484–490, Melbourne, Australia. Association for Computational Linguistics. find
  9. Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, and Noah A. Smith. 2015. Transition-based dependency parsing with stack long short-term memory. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural… find our card
  10. Adam Ek and Jean-Philippe Bernardy. 2020. How much of enhanced UD is contained in UD? In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 221–226, Online. Association for Computational Lingui… find our card
  11. Stefan Grünewald and Annemarie Friedrich. 2020. RobertNLP at the IWPT 2020 shared task: Surprisingly simple enhanced UD parsing for English. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pag… find our card
  12. Han He and Jinho D. Choi. 2020. Adaptation of multilingual transformer encoder for robust enhanced Universal Dependency parsing. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 181– 191,… find
  13. Daniel Hershcovich, Miryam de Lhoneux, Artur Kulmizev, Elham Pejhan, and Joakim Nivre. 2020. Køpsala: Transition-based graph parsing via efficient training and effective encoding. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing int… find
  14. Jenna Kanerva, Filip Ginter, and Sampo Pyysalo. 2020. Turku enhanced parser pipeline: From raw text to enhanced graphs in the IWPT 2020 shared task. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependenci… find
  15. Eliyahu Kiperwasser and Yoav Goldberg. 2016. Simple and accurate dependency parsing using bidirectional LSTM feature representations. Transactions of the Association for Computational Linguistics, 4:313–327. find our card
  16. Dan Kondratyuk and Milan Straka. 2019. 75 languages, 1 model: Parsing Universal Dependencies universally. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2779–279… find our card
  17. Matthias Lindemann, Jonas Groschwitz, and Alexander Koller. 2019. Compositional semantic parsing across graphbanks. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4576–4585, Florence, Italy. Association for Computational Linguistics. find
  18. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. find
  19. Marie-Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning. 2006. Generating typed dependency parses from phrase structure trees. In LREC. find
  20. Minh Van Nguyen, Viet Dac Lai, Amir Pouran Ben Veyseh, and Thien Huu Nguyen. 2021. Trankit: A light-weight transformer-based toolkit for multilingual natural language processing. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System De… find our card
  21. Joakim Nivre, Paola Marongiu, Filip Ginter, Jenna Kanerva, Simonetta Montemagni, Sebastian Schuster, and Maria Simi. 2018. Enhancing Universal Dependency treebanks: A case study. In Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), pages 102–107, Brussels, Belgium. Association… find our card
  22. Stephan Oepen, Omri Abend, Jan Hajic, Daniel Hershcovich, Marco Kuhlmann, Tim O’Gorman, Nianwen Xue, Jayeol Chun, Milan Straka, and Zdenka Uresova. 2019. find
  23. MRP 2019: Cross-framework meaning representation parsing. In Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning, pages 1–27, Hong Kong. Association for Computational Linguistics. find
  24. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A python natural language processing toolkit for many human languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 101– 108, Online.… find our card
  25. 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… find our card
  26. 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
  27. Milan Straka and Jana Straková. 2019. ÚFAL MRPipe at MRP 2019: UDPipe goes semantic in the meaning representation parsing shared task. In Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning, pages 127–137, Hong Kong.… find
  28. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. find
  29. Xinyu Wang, Yong Jiang, and Kewei Tu. 2020. Enhanced Universal Dependency parsing with second-order inference and mixture of training data. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages… find
  30. Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Łukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, N… find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/barry-2021-dcu-epfl-enhanced-dependency-parser/