Mova0.5 pre-release⌕
☰
home / docs / papers / English / Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures

Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures

What it is about

Event factuality prediction gives a real score in [−3, +3] for an event mention. Cue words that set the factuality can be far from the event word in the sentence, and a dependency tree can reach them while a sequential model can weigh them by meaning. The model has three parts: BERT and two BiLSTM layers for the sentence; an importance matrix over token pairs, made of a semantic part (from the LSTM states) and a syntactic part (1 for dependency edges, with self-loops and reverse edges), mixed by a weight λ; and a two-layer GCN with attention on the anchor word. On four benchmarks (FactBank, UW, MEANTIME, UDS-IH2) the model reports a new state of the art. In the ablation on the multi-dataset setting, the syntax-only version (λ = 1) gets MAE 0.310 and r 0.903 on FactBank; the semantic-only version (λ = 0) gets MAE 0.314 and r 0.867. The best λ is 0.6 for three datasets and 0.8 for UDS-IH2.

Ideas

For Mova

The chapter is 13. Verbs (modal auxiliaries and their role in factuality) and 27. Negation (negation as cue). The code is en/src/parse.rs (dependency arcs), prag/src/infer.rs (factuality score). Measures: MAE and Pearson on FactBank dev for the rule score, with the λ-mix and the random-weight control; run twice. The neural model is a comparison only.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/p19-1432

@inproceedings{veyseh2019graph,
  title = {{Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures}},
  author = {Veyseh, Amir Pouran Ben and Nguyen, Thien Huu and Dou, Dejing},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1432},
  url = {https://doi.org/10.18653/v1/p19-1432}
}

References

28 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Heike Adel and Hinrich Schütze. 2017. Exploring different dimensions of attention for uncertainty detection. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 22–34. find
  2. Marie-Catherine De Marneffe, Christopher D Manning, and Christopher Potts. 2012. Did it happen? the pragmatic complexity of veridicality assessment. Computational linguistics, 38(2):301–333. find
  3. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. ↗
  4. Mona T Diab, Lori Levin, Teruko Mitamura, Owen Rambow, Vinodkumar Prabhakaran, and Weiwei Guo. 2009. Committed belief annotation and tagging. In Proceedings of the Third Linguistic Annotation Workshop, pages 68–73. Association for Computational Linguistics. find
  5. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. ↗
  6. Kenton Lee, Yoav Artzi, Yejin Choi, and Luke Zettlemoyer. 2015. Event detection and factuality assessment with non-expert supervision. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1643–1648. find
  7. Amnon Lotan, Asher Stern, and Ido Dagan. 2013. Truthteller: Annotating predicate truth. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 752–757. find
  8. Weiyi Lu and Thien Huu Nguyen. 2018. Similar but not the same: Word sense disambiguation improves event detection via neural representation matching. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  9. Ana Marasovic and Anette Frank. 2016. Multilingual modal sense classification using a convolutional neural network. Proceedings of the 1st Workshop on Representation Learning for NLP, Rep4NLP@ACL 2016, Berlin, Germany, August 11, 2016, pages 111–120. find
  10. A-L Minard, Manuela Speranza, Ruben Urizar, Begona Altuna, MGJ van Erp, AM Schoen, CM van Son, et al. 2016. Meantime, the newsreader multilingual event and time corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016). Portorož, Slovenia. find
  11. Teruko Mitamura, Zhengzhong Liu, and Eduard Hovy. 2015. Overview of tac kbp 2015 event nugget track. In Proceedings of Text Analysis Conference (TAC). find
  12. Rowan Nairn, Cleo Condoravdi, and Lauri Karttunen. 2006. Computing relative polarity for textual inference. In Proceedings of the fifth international workshop on inference in computational semantics (icos-5). find our card
  13. Thien Huu Nguyen, Kyunghyun Cho, and Ralph Grishman. 2016a. Joint event extraction via recurrent neural networks. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). find
  14. Thien Huu Nguyen, Lisheng Fu, Kyunghyun Cho, and Ralph Grishman. 2016b. A two-stage approach for extending event detection to new types via neural networks. In Proceedings of the 1st ACL Workshop on Representation Learning for NLP (RepL4NLP). find
  15. Thien Huu Nguyen and Ralph Grishman. 2015b. Event detection and domain adaptation with convolutional neural networks. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find
  16. Thien Huu Nguyen and Ralph Grishman. 2018. Graph convolutional networks with argument-aware pooling for event detection. In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI). find
  17. Thien Huu Nguyen, Adam Meyers, and Ralph Grishman. 2016g. New york university 2016 system for kbp event nugget: A deep learning approach. In Proceedings of Text Analysis Conference (TAC). find
  18. Thien Huu Nguyen, Avirup Sil, Georgiana Dinu, and Radu Florian. 2016d. Toward mention detection robustness with recurrent neural networks. In Proceedings of IJCAI Workshop on Deep Learning for Artificial Intelligence (DLAI). find
  19. Trung Minh Nguyen and Thien Huu Nguyen. 2019. One for all: Neural joint modeling of entities and events. In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI). find
  20. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543. find
  21. Vinodkumar Prabhakaran, Owen Rambow, and Mona Diab. 2010. Automatic committed belief tagging. In Proceedings of the 23rd International Conference on Computational Linguistics: Posters, pages 1014– 1022. Association for Computational Linguistics. find
  22. Zhong Qian, Peifeng Li, Yue Zhang, Guodong Zhou, and Qiaoming Zhu. 2018. Event factuality identification via generative adversarial networks with auxiliary classification. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, July 13-19, 2018, Stockholm, Sweden., pages 4293–4300. find
  23. Zhong Qian, Peifeng Li, and Qiaoming Zhu. 2015. A two-step approach for event factuality identification. In Asian Language Processing (IALP), 2015 International Conference on, pages 103–106. IEEE. find
  24. Rachel Rudinger, Aaron Steven White, and Benjamin Van Durme. 2018. Neural models of factuality. 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 731–744. find our card
  25. Roser Saurı́. 2008. A factuality profiler for eventualities in text. Unveröffentlichte Dissertation, Brandeis University. Zugriff auf http://www.cs. brandeis. edu/˜ roser/pubs/sauriDiss, 1. ↗
  26. Roser Saurı́ and James Pustejovsky. 2009. Factbank: a corpus annotated with event factuality. Language resources and evaluation, 43(3):227. find
  27. Roser Saurı́ and James Pustejovsky. 2012. Are you sure that this happened? assessing the factuality degree of events in text. Computational Linguistics, 38(2):261–299. find
  28. Gabriel Stanovsky, Judith Eckle-Kohler, Yevgeniy Puzikov, Ido Dagan, and Iryna Gurevych. 2017. Integrating deep linguistic features in factuality prediction over unified datasets. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), volume 2, pages 352–357. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/veyseh-2019-graph-based-neural-networks-event/