Elamur Research⌕
☰
home / papers / 2020 / A Novel Cascade Binary Tagging Framework for Relational Triple Extraction

A Novel Cascade Binary Tagging Framework for Relational Triple Extraction

Summary

Relational triple extraction pulls (subject, relation, object) facts out of raw sentences, a core step in building knowledge graphs. It becomes difficult when several triples in one sentence share entities, as in the EntityPairOverlap (EPO) and SingleEntityOverlap (SEO) patterns. Earlier joint approaches, such as Seq2Seq models with copying or the GCN-based GraphRel, still assign a relation label to each entity pair. That design suffers from heavy class imbalance and gets confused when one entity takes part in several facts.

The authors define the training likelihood directly over whole triples. They then treat every relation as a mapping from a subject to its object(s), which may be empty. Their model, CasRel, works in two stages on top of a BERT encoder:

  • it first marks subject spans;
  • for each detected subject, it runs one binary object tagger per relation.

On the public NYT and WebNLG datasets, CasRel beats the strongest earlier systems by a wide margin. Even with a randomly initialized encoder it already outperforms them. The gains hold across all overlap types and are largest for sentences containing many triples, which makes the method well suited to dense, entity-rich text.

Key points

  • Core idea: instead of a classifier f(s, o) → r, CasRel learns one tagger per relation, f_r(s) → o. This lets the model handle overlapping triples without extra machinery.
  • With a pre-trained BERT encoder, CasRel exceeds the best baseline by 17.5 F1 points on NYT and 30.2 F1 points on WebNLG. The variants CasRel_random and CasRel_LSTM also stay strong on both datasets.
  • Baselines do much worse on WebNLG, where EPO and SEO sentences dominate, than on NYT, where most sentences are Normal. CasRel performs consistently on both.
  • For sentences with five or more triples, CasRel reaches an F1 of 83.7 on NYT and 90.9 on WebNLG. This is +37.8 and +35.2 over CopyR_RL, the strongest baseline in that comparison.
  • Code and data are released at github.com/weizhepei/CasRel (ACL 2020).

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: Natural language processing

Cited by

83 papers of our library cite it (of the 140884 whose bibliographies we read); 2 of them have a page here, 81 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.acl-main.136

@inproceedings{wei2020novel,
  title = {{A Novel Cascade Binary Tagging Framework for Relational Triple Extraction}},
  author = {Wei, Zhepei and Su, Jianlin and Wang, Yue and Tian, Yuan and Chang, Yi},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.acl-main.136},
  url = {https://doi.org/10.18653/v1/2020.acl-main.136}
}

References

31 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary Ives. 2007. Dbpedia: A nucleus for a web of open data. In Proceedings of the 6th International The Semantic Web and 2nd Asian Conference on Asian Semantic Web Conference, pages 722–735. of the 55th Annual Mee… find
  2. Matthew R Gormley, Mo Yu, and Mark Dredze. 2015. Improved relation extraction with feature-rich compositional embedding models. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1774–1784. find
  3. Pankaj Gupta, Hinrich Schütze, and Bernt Andrassy. 2016. Table filling multi-task recurrent neural network for joint entity and relation extraction. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2537–2547. find
  4. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD international conference on Management of data, pages 1247–1250. find
  5. Raphael Hoffmann, Congle Zhang, Xiao Ling, Luke Zettlemoyer, and Daniel S Weld. 2011. Knowledge-based weak supervision for information extraction of overlapping relations. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1… find
  6. Yee Seng Chan and Dan Roth. 2011. Exploiting syntactico-semantic structures for relation extraction. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1, pages 551– 560. Association for Computational Linguistics. find
  7. Arzoo Katiyar and Claire Cardie. 2017. Going out on a limb: Joint extraction of entity mentions and relations without dependency trees. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 917–928. find
  8. Dai Dai, Xinyan Xiao, Yajuan Lyu, Shan Dou, Qiaoqiao She, and Haifeng Wang. 2019. Joint extraction of entities and overlapping relations using position-attentive sequence labeling. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 6300–6308. find
  9. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. find
  10. 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
  11. Xin Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun, and Wei Zhang. 2014. Knowledge vault: A web-scale approach to probabilistic knowledge fusion. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data m… find
  12. Tsu-Jui Fu, Peng-Hsuan Li, and Wei-Yun Ma. 2019. Graphrel: Modeling text as relational graphs for joint entity and relation extraction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1409–1418. find
  13. Claire Gardent, Anastasia Shimorina, Shashi Narayan, and Laura Perez-Beltrachini. 2017. Creating training corpora for nlg micro-planners. In Proceedings Qi Li and Heng Ji. 2014. Incremental joint extraction of entity mentions and relations. In Proceedings of the 52nd Annual Meeting of the Associatio… find our card
  14. Xiaoya Li, Fan Yin, Zijun Sun, Xiayu Li, Arianna Yuan, Duo Chai, Mingxin Zhou, and Jiwei Li. 2019. Entity-relation extraction as multi-turn question answering. In Annual Meeting of the Association for Computational Linguistics (ACL). find our card
  15. Liyuan Liu, Xiang Ren, Qi Zhu, Shi Zhi, Huan Gui, Heng Ji, and Jiawei Han. 2017. Heterogeneous supervision for relation extraction: A representation learning approach. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 46–56. find
  16. Mike Mintz, Steven Bills, Rion Snow, and Dan Jurafsky. 2009. Distant supervision for relation extraction without labeled data. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2… find
  17. Makoto Miwa and Mohit Bansal. 2016. End-to-end relation extraction using lstms on sequences and tree structures. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 1105– 1116. of the 2019 Conference on Empirical Methods… find our card
  18. Makoto Miwa and Yutaka Sasaki. 2014. Modeling joint entity and relation extraction with table representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1858–1869. find our card
  19. Xiangrong Zeng, Daojian Zeng, Shizhu He, Kang Liu, and Jun Zhao. 2018. Extracting relational facts by an end-to-end neural model with copy mechanism. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 506–514. find our card
  20. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543. find
  21. Xiang Ren, Zeqiu Wu, Wenqi He, Meng Qu, Clare R Voss, Heng Ji, Tarek F Abdelzaher, and Jiawei Han. 2017. Cotype: Joint extraction of typed entities and relations with knowledge bases. In Proceedings of the 26th International Conference on World Wide Web, pages 1015–1024. find
  22. Sebastian Riedel, Limin Yao, and Andrew McCallum. 2010. Modeling relations and their mentions without labeled text. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 148–163. find
  23. Ryuichi Takanobu, Tianyang Zhang, Jiexi Liu, and Minlie Huang. 2019. A hierarchical framework for relation extraction with reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 7072–7079. find
  24. Suncong Zheng, Feng Wang, Hongyun Bao, Yuexing Hao, Peng Zhou, and Bo Xu. 2017. Joint extraction of entities and relations based on a novel tagging scheme. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 1227–1236. find our card
  25. Peixiang Zhong, Di Wang, and Chunyan Miao. 2019. Knowledge-enriched transformer for emotion detection in textual conversations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-I… find our card
  26. GuoDong Zhou, Jian Su, Jie Zhang, and Min Zhang. 2005. Exploring various knowledge in relation extraction. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL05), pages 427–434. find our card
  27. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems, pages 5998–6008. find
  28. Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, et al. 2016. Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144. find
  29. Xiaofeng Yu and Wai Lam. 2010. Jointly identifying entities and extracting relations in encyclopedia text via a graphical model approach. In Proceedings of the 23rd International Conference on Computational Linguistics: Posters, pages 1399–1407. Association for Computational Linguistics. find
  30. Dmitry Zelenko, Chinatsu Aone, and Anthony Richardella. 2003. Kernel methods for relation extraction. Journal of machine learning research, 3(Feb):1083–1106. find our card
  31. Xiangrong Zeng, Shizhu He, Daojian Zeng, Kang Liu, Shengping Liu, and Jun Zhao. 2019. Learning the extraction order of multiple relational facts in a sentence with reinforcement learning. In Proceedings find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wei-2020-novel-cascade-binary-tagging-framework/