Elamur Research⌕
☰
home / papers / 2024 / Bilingual Rhetorical Structure Parsing with Large Parallel Annotations

Bilingual Rhetorical Structure Parsing with Large Parallel Annotations

Summary

Cross-lingual RST discourse parsing has been held back by a lack of parallel data and by inconsistent annotation practices across corpora and languages. To address this, Chistova built RRG, a Russian counterpart of the full RST layer of the English GUM 9.1 corpus. All 213 documents were translated by hand rather than by EDU-level machine translation. They were then aligned to the original trees unit by unit, with Russian segmentation following the RRT guidelines and relations following GUM rules. On this data, the author trains an end-to-end top-down unified parser built on the multilingual XLM-RoBERTa encoder. It sets state-of-the-art results on RST-DT, GUM, RRT and RRG. An English-only model parses Russian almost as well as a Russian-trained one, but transfer in the opposite direction suffers, mainly because segmentation differs between the languages. Training on both languages gives the best Russian scores. The work is the first to assess end-to-end cross-lingual discourse parsing using a parallel corpus whose RST annotations were produced by hand.

Key points

  • RRG resource: 213 documents across 12 genres with 25,223 EDUs. Each document took up to about 2.5 hours to produce. Data, code and models are released at github.com/tchewik/BilingualRSP.
  • End-to-end Full F1:
    • RST-DT: 53.0
    • GUM: 47.9 (English model) and 47.6 (bilingual model)
    • RRT: 45.3
    • RRG: 44.6 (Russian model) and 45.4 (bilingual model)
  • Russian-to-English transfer: English segmentation drops to 86.9% F1. The cause is the Russian segmenter's reliance on commas, which end 37.5% of EDUs in RRG but only 18.5% in GUM.
  • Amount of second-language data: With partial target-language annotation, accuracy of relation labels levels off at roughly 50% of the target data.
  • Genre effects: The bilingual model improves Russian parsing in 9 of 12 genres. Spoken genres score lowest but gain the most (conversation rises from 22.1 to 27.4 F1).

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: Discourse analysis

Cited by

6 papers of our library cite it (of the 140673 whose bibliographies we read).

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2024.findings-acl.577 · arXiv 2409.14969

@inproceedings{chistova2024bilingual,
  title = {{Bilingual Rhetorical Structure Parsing with Large Parallel Annotations}},
  author = {Chistova, Elena},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2024},
  year = {2024},
  doi = {10.18653/v1/2024.findings-acl.577},
  eprint = {2409.14969},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2024.findings-acl.577}
}

References

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

  1. Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5:135–146. ↗
  2. Chloé Braud, Maximin Coavoux, and Anders Søgaard. 2017. Cross-lingual RST discourse parsing. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 292–304, Valencia, Spain. Association for Computational Linguistics. ↗ our card
  3. Chloé Braud, Yang Janet Liu, Eleni Metheniti, Philippe Muller, Laura Rivière, Attapol Rutherford, and Amir Zeldes. 2023. find
  4. The DISRPT 2023 shared task on elementary discourse unit segmentation, connective detection, and relation classification. In Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023), pages 1–21, Toronto, Canada. The Association for Computational Linguistics. In Proceedings of the Second SIGdial Workshop on Discourse and Dialogue. find our card
  5. Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni St John, Noah Constant, Mario Guajardo-Cespedes, Steve Yuan, Chris Tar, et al. 2018. Universal Sentence Encoder. arXiv preprint arXiv:1803.11175. ↗ our card
  6. Elena Chistova, Artem Shelmanov, Dina Pisarevskaya, Maria Kobozeva, Vadim Isakov, Alexander Panchenko, Svetlana Toldova, and Ivan Smirnov. 2021. RST discourse parser for Russian: an experimental study of deep learning models. In Analysis of Images, Social Networks and Texts: 9th International Conference, AIST 2020, Skolkovo, Moscow, Russia, October 15–16, 2020, Revised Selected Papers 9, pages 105–119. Springer. find
  7. Elena Chistova and Ivan Smirnov. 2022. Discourse-aware text classification for argument mining. In Computational Linguistics and Intellectual Technologies. Papers from the Annual International Conference "Dialogue" (2022), 21, pages 93–105. find
  8. 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 for Computational Linguistics, pages 8440– 8451, Online. Association for Computational Linguistics. ↗
  9. Iria Da Cunha and Mikel Iruskieta. 2010. Comparing rhetorical structures in different languages: The influence of translation strategies. Discourse Studies, 12(5):563–598. ↗
  10. Chloé Braud, Barbara Plank, and Anders Søgaard. 2016. Multi-view and multi-task training of RST discourse parsers. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1903–1913, Osaka, Japan. find our card
  11. The COLING 2016 Organizing Committee. find
  12. Vanessa Wei Feng and Graeme Hirst. 2014. A linear-time bottom-up discourse parser with constraints and post-editing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 511–521, Baltimore, Maryland. Association for Computational Linguistics. find our card
  13. Shuyuan Cao. 2020. How does discourse affect Spanish-Chinese translation? a case study based on a Spanish-Chinese parallel corpus. In Proceedings of the First Workshop on Computational Approaches to Discourse, pages 1–10, Online. Association for Computational Linguistics. find
  14. Xianghua Fu, Wangwang Liu, Yingying Xu, Chong Yu, and Ting Wang. 2016. Long short-term memory network over rhetorical structure theory for sentence-level sentiment analysis. In Proceedings of The 8th Asian Conference on Machine Learning, pages 17– 32. PMLR. find
  15. Shuyuan Cao, Iria da Cunha, and Mikel Iruskieta. 2018. The RST Spanish-Chinese treebank. In Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), pages 156–166, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find
  16. Naman Goyal and Jacob Eisenstein. 2016. A joint model of rhetorical discourse structure and summarization. In Proceedings of the Workshop on Structured Prediction for NLP, pages 25–34, Austin, TX. Association for Computational Linguistics. find
  17. Lynn Carlson, Daniel Marcu, and Mary Ellen Okurovsky. 2001. Building a discourse-tagged corpus in the framework of Rhetorical Structure Theory. ↗ our card
  18. Francisco Guzmán, Shafiq Joty, Lluís Màrquez, and Preslav Nakov. 2014. Using discourse structure improves machine translation evaluation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 687–698, Baltimore, Maryland. Association for Computational Linguistics. find
  19. Katsuhiko Hayashi, Tsutomu Hirao, and Masaaki Nagata. 2016. Empirical comparison of dependency conversions for RST discourse trees. In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 128–136, Los Angeles. Association for Computational Linguistics. find
  20. Patrick Huber and Giuseppe Carenini. 2020. MEGA RST discourse treebanks with structure and nuclearity from scalable distant sentiment supervision. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7442–7457, Online. Association for Computational Linguistics. find our card
  21. Mikel Iruskieta and Chloé Braud. 2019. EusDisParser: improving an under-resourced discourse parser with cross-lingual data. In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019, pages 62–71, Minneapolis, MN. Association for Computational Linguistics. find our card
  22. Mikel Iruskieta, Iria Da Cunha, and Maite Taboada. 2015. A qualitative comparison method for rhetorical structures: identifying different discourse structures in multilingual corpora. Language resources and evaluation, 49:263–309. ↗
  23. Yangfeng Ji and Jacob Eisenstein. 2014. Representation learning for text-level discourse parsing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13–24, Baltimore, Maryland. Association for Computational Linguistics. find our card
  24. Shafiq Joty, Giuseppe Carenini, and Raymond Ng. 2012. A novel discriminative framework for sentence-level discourse analysis. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 904–915, Jeju Island, Korea. Association for Computational Linguistics. find
  25. Shafiq Joty, Giuseppe Carenini, and Raymond T. Ng. 2015. CODRA: A novel discriminative framework for rhetorical analysis. Computational Linguistics, 41(3):385–435. ↗ our card
  26. Sopan Khosla, James Fiacco, and Carolyn Rosé. 2021. Evaluating the impact of a hierarchical discourse representation on entity coreference resolution performance. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1645–1651, Online. Association for Computational Linguistics. find
  27. Naoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura, and Masaaki Nagata. 2020. Top-down rst parsing utilizing granularity levels in documents. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):8099–8106. find
  28. Naoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura, and Masaaki Nagata. 2022. A simple and strong baseline for end-to-end neural RST-style discourse parsing. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6725–6737, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. ↗ our card
  29. Fajri Koto, Jey Han Lau, and Timothy Baldwin. 2021. Top-down discourse parsing via sequence labelling. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 715–726, Online. Association for Computational Linguistics. ↗ our card
  30. Murathan Kurfalı and Robert Östling. 2021. Probing multilingual language models for discourse. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 8–19, Online. Association for Computational Linguistics. ↗
  31. Jing Li, Aixin Sun, and Shafiq Joty. 2018. SegBot: a generic neural text segmentation model with pointer network. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pages 4166–4172. find
  32. Qi Li, Tianshi Li, and Baobao Chang. 2016. Discourse parsing with attention-based hierarchical neural networks. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 362–371, Austin, Texas. Association for Computational Linguistics. find our card
  33. Xiang Lin, Shafiq Joty, Prathyusha Jwalapuram, and M Saiful Bari. 2019. A unified linear-time framework for sentence-level discourse parsing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4190–4200, Florence, Italy. Association for Computational Linguistics. find our card
  34. Shikun Liu, Edward Johns, and Andrew J Davison. 2019. End-to-end multi-task learning with attention. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1871–1880. find
  35. Yang Janet Liu and Amir Zeldes. 2023. Why can’t discourse parsing generalize? a thorough investigation of the impact of data diversity. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3112– 3130, Dubrovnik, Croatia. Association for Computational Linguistics. ↗ our card
  36. Zhengyuan Liu, Ke Shi, and Nancy Chen. 2020. Multilingual neural RST discourse parsing. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6730–6738, Barcelona, Spain (Online). International Committee on Computational Linguistics. ↗ our card
  37. Zhengyuan Liu, Ke Shi, and Nancy Chen. 2021. DMRST: A joint framework for document-level multilingual RST discourse segmentation and parsing. In Proceedings of the 2nd Workshop on Computational Approaches to Discourse, pages 154–164, Punta Cana, Dominican Republic and Online. Association for Computational Linguistics. ↗
  38. Amandla Mabona, Laura Rimell, Stephen Clark, and Andreas Vlachos. 2019. Neural generative rhetorical structure parsing. 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 2284–2295, Hong Kong, China. Association for Computational Linguistics. ↗ our card
  39. Eleni Metheniti, Chloé Braud, Philippe Muller, and Laura Rivière. 2023. DisCut and DiscReT: MELODI at DISRPT 2023. In Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023), pages 29–42, Toronto, Canada. The Association for Computational Linguistics. find
  40. Philippe Muller, Chloé Braud, and Mathieu Morey. 2019. ToNy: Contextual embeddings for accurate multilingual discourse segmentation of full documents. In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019, pages 115– 124, Minneapolis, MN. Association for Computational Linguistics. find
  41. Bita Nejat, Giuseppe Carenini, and Raymond Ng. 2017. Exploring joint neural model for sentence level discourse parsing and sentiment analysis. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 289–298, Saarbrücken, Germany. Association for Computational Linguistics. find our card
  42. Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty, and Xiaoli Li. 2021. RST parsing from scratch. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1613–1625, Online. Association for Computational Linguistics. find
  43. Siyao Peng, Yang Janet Liu, and Amir Zeldes. 2022. GCDT: A Chinese RST treebank for multigenre and multilingual discourse parsing. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 382–391, Online only. Association for Computational Linguistics. ↗ our card
  44. Dina Pisarevskaya, Margarita Ananyeva, Maria Kobozeva, Alexander Nasedkin, Sofia Nikiforova, Irina Pavlova, and Alexey Shelepov. 2017. Towards building a discourse-annotated corpus of Russian. In Computational Linguistics and Intellectual Technologies. Papers from the Annual International Conference "Dialogue" (2017), pages 201–212. find
  45. Radu Soricut and Daniel Marcu. 2003. Sentence level discourse parsing using syntactic and lexical information. In Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 228–235. find our card
  46. Mihai Surdeanu, Tom Hicks, and Marco Antonio Valenzuela-Escárcega. 2015. Two practical Rhetorical Structure Theory parsers. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pages 1–5, Denver, Colorado. Association for Computational Linguistics. find our card
  47. Zhiguo Wang, Wael Hamza, and Radu Florian. 2017. Bilateral multi-perspective matching for natural language sentences. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, page 4144–4150. AAAI Press. find our card
  48. Nan Yu, Meishan Zhang, and Guohong Fu. 2018. Transition-based neural RST parsing with implicit syntax features. In Proceedings of the 27th International Conference on Computational Linguistics, pages 559–570, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find
  49. Nan Yu, Meishan Zhang, Guohong Fu, and Min Zhang. 2022. RST discourse parsing with second-stage EDU-level pre-training. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4269– 4280, Dublin, Ireland. Association for Computational Linguistics. find our card
  50. Amir Zeldes. 2017. The GUM corpus: Creating multilayer resources in the classroom. Language Resources and Evaluation, 51(3):581–612. ↗
  51. Amir Zeldes, Debopam Das, Erick Galani Maziero, Juliano Antonio, and Mikel Iruskieta. 2019. find
  52. The DIS-RPT 2019 shared task on elementary discourse unit segmentation and connective detection. In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019, pages 97–104, Minneapolis, MN. Association for Computational Linguistics. find
  53. Amir Zeldes, Yang Janet Liu, Mikel Iruskieta, Philippe Muller, Chloé Braud, and Sonia Badene. 2021. find
  54. The DISRPT 2021 shared task on elementary discourse unit segmentation, connective detection, and relation classification. In Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021), pages 1–12, Punta Cana, Dominican Republic. Association for Computational Linguistics. find our card
  55. Longyin Zhang, Fang Kong, and Guodong Zhou. 2021a. Adversarial learning for discourse rhetorical structure parsing. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3946–3957, Online. Association for Computational Linguistics. find our card
  56. Longyin Zhang, Yuqing Xing, Fang Kong, Peifeng Li, and Guodong Zhou. 2020. A top-down neural architecture towards text-level parsing of discourse rhetorical structure. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6386–6395, Online. Association for Computational Linguistics. find our card
  57. Ying Zhang, Hidetaka Kamigaito, and Manabu Okumura. 2021b. A language model-based generative classifier for sentence-level discourse parsing. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2432– 2446, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. find

↑ back to top