Skip to main content

Advertisement

Log in

Document-Level Event Factuality Identification via Reinforced Semantic Learning Network

  • Regular Paper
  • Artificial Intelligence and Pattern Recognition
  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

This paper focuses on document-level event factuality identification (DEFI), which predicts the factual nature of an event from the view of a document. As the document-level sub-task of event factuality identification (EFI), DEFI is a challenging and fundamental task in natural language processing (NLP). Currently, most existing studies focus on sentence-level event factuality identification (SEFI). However, DEFI is still in the early stage and related studies are quite limited. Previous work is heavily dependent on various NLP tools and annotated information, e.g., dependency trees, event triggers, speculative and negative cues, and does not consider filtering irrelevant and noisy texts that can lead to wrong results. To address these issues, this paper proposes a reinforced multi-granularity hierarchical network model: Reinforced Semantic Learning Network (RSLN), which means it can learn semantics from sentences and tokens at various levels of granularity and hierarchy. Since integrated with hierarchical reinforcement learning (HRL), the RSLN model is able to select relevant and meaningful sentences and tokens. Then, RSLN encodes the event and document according to these selected texts. To evaluate our model, based on the DLEF (Document-Level Event Factuality) corpus, we annotate the ExDLEF corpus as the benchmark dataset. Experimental results show that the RSLN model outperforms several state-of-the-arts.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Rudinger R, White A S, Van Durme B. Neural models of factuality. In Proc. the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun. 2018, pp.731–744. DOI: https://doi.org/10.18653/v1/n18-1067.

    Google Scholar 

  2. Qian Z, Li P, Zhou G, Zhu Q. Event factuality identification via hybrid neural networks. In Proc. the 25th International Conference on Neural Information Processing, Dec. 2018, pp.335–347. DOI: https://doi.org/10.1007/978-3-030-04221-9_30.

    Chapter  MATH  Google Scholar 

  3. Qian Z, Li P, Zhang Y, Zhou G, Zhu Q. Event factuality identification via generative adversarial networks with auxiliary classification. In Proc. the 27th International Joint Conference on Artificial Intelligence, Jul. 2018, pp.4293–4300. DOI: https://doi.org/10.24963/ijcai.2018/597.

    MATH  Google Scholar 

  4. Sheng J, Zou B, Gong Z, Hong Y, Zhou G. Chinese event factuality detection. In Proc. the 8th CCF International Conference on Natural Language Processing and Chinese Computing, Oct. 2019, pp.486–496. DOI: https://doi.org/10.1007/978-3-030-32236-6_44.

    Google Scholar 

  5. Veyseh A P B, Nguyen T H, Dou D. Graph based neural networks for event factuality prediction using syntactic and semantic structures. In Proc. the 57th Conference of the Association for Computational Linguistics, Oct. 2019, pp.4393–4399. DOI: https://doi.org/10.18653/v1/p19-1432.

    MATH  Google Scholar 

  6. Qian Z, Li P, Zhu Q, Zhou G. Document-level event factuality identification via adversarial neural network. In Proc. the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun. 2019, pp.2799–2809. DOI: https://doi.org/10.18653/v1/n19-1287.

    MATH  Google Scholar 

  7. Huang R, Zou B, Wang H, Li P, Zhou G. Event factuality detection in discourse. In Proc. the 8th CCF International Conference on Natural Language Processing and Chinese Computing, Oct. 2019, pp.404–414. DOI: https://doi.org/10.1007/978-3-030-32236-6_36.

    MATH  Google Scholar 

  8. Cao P, Chen Y, Yang Y, Liu K, Zhao J. Uncertain local-to-global networks for document-level event factuality identification. In Proc. the 2021 Conference on Empirical Methods in Natural Language Processing, Nov. 2021, pp.2636–2645. DOI: https://doi.org/10.18653/v1/2021.emnlp-main.207.

    Chapter  MATH  Google Scholar 

  9. Liu J, Pan F, Luo L. GoChat: Goal-oriented chatbots with hierarchical reinforcement learning. In Proc. the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2020, pp.1793–1796. DOI: https://doi.org/10.1145/3397271.3401250.

    MATH  Google Scholar 

  10. Wang J, Sun C, Li S, Wang J, Si L, Zhang M, Liu X, Zhou G. Human-like decision making: Document-level aspect sentiment classification via hierarchical reinforcement learning. In Proc. the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Nov. 2019, pp.5580–5589. DOI: https://doi.org/10.18653/v1/D19-1560.

    Chapter  MATH  Google Scholar 

  11. Xiao L, Wang L, He H, Jin Y. Copy or rewrite: Hybrid summarization with hierarchical reinforcement learning. In Proc. the 34th AAAI Conference on Artificial Intelligence, Feb. 2020, pp.9306–9313. DOI: https://doi.org/10.1609/AAAI.V34I05.6470.

    MATH  Google Scholar 

  12. Wan G, Pan S, Gong C, Zhou C, Haffari G. Reasoning like human: Hierarchical reinforcement learning for knowledge graph reasoning. In Proc. the 29th International Joint Conference on Artificial Intelligence, Jul. 2020, pp.1926–1932. DOI: https://doi.org/10.24963/ijcai.2020/267.

    MATH  Google Scholar 

  13. Zhou X, Luo S, Wu Y. Co-attention hierarchical network: Generating coherent long distractors for reading comprehension. In Proc. the 34th AAAI Conference on Artificial Intelligence, Feb. 2020, pp.9725–9732. DOI: https://doi.org/10.1609/AAAI.V34I05.6522.

    Google Scholar 

  14. Wu L, Rao Y, Zhao Y, Liang H, Nazir A. DTCA: Decision tree-based co-attention networks for explainable claim verification. In Proc. the 58th Annual Meeting of the Association for Computational Linguistics, Jul. 2020, pp.1024–1035. DOI: https://doi.org/10.18653/v1/2020.acl-main.97.

    Chapter  MATH  Google Scholar 

  15. Wu Y, Zhan P, Zhang Y, Wang L, Xu Z. Multimodal fusion with co-attention networks for fake news detection. In Proc. the 2021 Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, Aug. 2021, pp.2560–2569. DOI: https://doi.org/10.18653/v1/2021.findings-acl.226.

    Chapter  MATH  Google Scholar 

  16. Lai T M, Tran Q H, Bui T, Kihara D. A gated self-attention memory network for answer selection. In Proc. the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Nov. 2019, pp.5953–5959. DOI: https://doi.org/10.18653/v1/D19-1610.

    MATH  Google Scholar 

  17. Xue L, Li X, Zhang N L. Not all attention is needed: Gated attention network for sequence data. In Proc. the 34th AAAI Conference on Artificial Intelligence, Feb. 2020, pp.6550–6557. DOI: https://doi.org/10.1609/AAAI.V34I04.6129.

    MATH  Google Scholar 

  18. Liu L, Chen H, Sun Y. A multi-classification sentiment analysis model of Chinese short text based on gated linear units and attention mechanism. Trans. Asian and Low-Resource Language Information Processing, 2021, 20(6): Article No. 109. DOI: https://doi.org/10.1145/3464425.

  19. Chen Z, Hui S C, Zhuang F, Liao L, Li F, Jia M, Li J. EvidenceNet: Evidence fusion network for fact verification. In Proc. the 2022 ACM Web Conference, Apr. 2022, pp.2636–2645. DOI: https://doi.org/10.1145/3485447.3512135.

    Chapter  MATH  Google Scholar 

  20. Chen J, Bao Q, Sun C, Zhang X, Chen J, Zhou H, Xiao Y, Li L. LOREN: Logic-regularized reasoning for interpretable fact verification. In Proc. the 36th AAAI Conference on Artificial Intelligence, Feb. 2022, pp.10482–10491. DOI: https://doi.org/10.1609/AAAI.V36I10.21291.

    MATH  Google Scholar 

  21. Ma J, Gao W, Joty S, Wong K F. Sentence-level evidence embedding for claim verification with hierarchical attention networks. In Proc. the 57th Annual Meeting of the Association for Computational Linguistics, Jul. 2019, pp.2561–2571. DOI: https://doi.org/10.18653/v1/p19-1244.

    Chapter  MATH  Google Scholar 

  22. Chen J, Zhang R, Guo J, Fan Y, Cheng X. GERE: Generative evidence retrieval for fact verification. In Proc. the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2022, pp.2184–2189. DOI: https://doi.org/10.1145/3477495.3531827.

    MATH  Google Scholar 

  23. Qian Z, Li P, Zhu Q, Zhou G. Document-level event factuality identification via reinforced multi-granularity hierarchical attention networks. In Proc. the 31st International Joint Conference on Artificial Intelligence, Jul. 2022, pp.4338–4345. DOI: https://doi.org/10.24963/ijcai.2022/602.

    Google Scholar 

  24. Pennington J, Socher R, Manning C D. GloVe: Global vectors for word representation. In Proc. the 2014 Conference on Empirical Methods in Natural Language Processing, Oct. 2014, pp.1532–1543. DOI: https://doi.org/10.3115/v1/d14-1162.

    Chapter  MATH  Google Scholar 

  25. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I. Attention is all you need. In Proc. the 31st International Conference on Neural Information Processing Systems, Dec. 2017, pp.5998–6008.

    Google Scholar 

  26. Zhang T, Huang M, Zhao L. Learning structured representation for text classification via reinforcement learning. In Proc. the 32nd AAAI Conference on Artificial Intelligence, Feb. 2018, pp.6053–6060. DOI: https://doi.org/10.1609/AAAI.V32I1.12047.

    MATH  Google Scholar 

  27. Williams R J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 1992, 8(3): 229–256. DOI: https://doi.org/10.1007/BF00992696.

    Article  MATH  Google Scholar 

  28. Sutton R S, McAllester D, Singh S, Mansour Y. Policy gradient methods for reinforcement learning with function approximation. In Proc. the 12th International Conference on Neural Information Processing Systems, Nov. 1999, pp.1057–1063.

    MATH  Google Scholar 

  29. Kingma D P, Ba J. Adam: A method for stochastic optimization. In Proc. 3rd International Conference on Learning Representations, 2015. DOI: https://doi.org/10.48550/arXiv.1412.6980.

    MATH  Google Scholar 

  30. Robbins H, Monro S. A stochastic approximation method. The Annals of Mathematical Statistics, 1951, 22(3): 400–407. DOI: https://doi.org/10.1214/aoms/1177729586.

    Article  MathSciNet  MATH  Google Scholar 

  31. Zhang H, Qian Z, Zhu X, Li P. Document-level event factuality identification using negation and speculation scope. In Proc. the 28th International Conference on Neural Information Processing, Dec. 2021, pp.414–425. DOI: https://doi.org/10.1007/978-3-030-92185-9_34.

    Chapter  MATH  Google Scholar 

  32. Devlin J, Chang M W, Lee K, Toutanova K. BERT: Pretraining of deep bidirectional transformers for language understanding. In Proc. the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun. 2019, pp.4171–4186. DOI: https://doi.org/10.18653/v1/n19-1423.

    MATH  Google Scholar 

  33. Duan J, Zhang Y, Ding X, Chang C Y, Liu T. Learning target-specific representations of financial news documents for cumulative abnormal return prediction. In Proc. the 27th International Conference on Computational Linguistics, Aug. 2018, pp.2823–2833.

    MATH  Google Scholar 

  34. Duan J, Ding X, Zhang Y, Liu T. TEND: A target-dependent representation learning framework for news document. IEEE/ACM Trans Audio, Speech, and Language Processing, 2019, 27(12): 2313–2325. DOI https://doi.org/10.1109/TASLP.2019.2947364.

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding authors

Correspondence to Zhong Qian  (钱 忠), Pei-Feng Li  (李培峰), Qiao-Ming Zhu  (朱巧明) or Guo-Dong Zhou  (周国栋).

Ethics declarations

Conflict of Interest The authors declare that they have no conflict of interest.

Additional information

The work was supported by the National Natural Science Foundation of China under Grant Nos. 62006167, 62276177, 62376181, and 62376178, the Natural Science Foundation of the Jiangsu Higher Education Institutions of China under Grant No. 24KJB520036, and the Project Funded by the Priority Academic Program Development (PAPD) of Jiangsu Higher Education Institutions.

Zhong Qian received his B.S. and Ph.D. degrees in computer science and technology from Soochow University, Suzhou, in 2012 and 2018, respectively. Currently, he is an associate professor in the School of Computer Science and Technology, Soochow University, Suzhou. His main research interest is information extraction in natural language processing.

Pei-Feng Li received his B.S., M.S., and Ph.D. degrees all in computer science from Soochow University, Suzhou, in 1994, 1997, and 2006, respectively. Currently, he is a professor at the School of Computer Science and Technology, and AI Research Institute, Soochow University, Suzhou. His current research interests include Chinese information processing, machine learning, and information extraction.

Qiao-Ming Zhu received his Ph.D. degree in computer science and technology from Soochow University, Suzhou, in 2008. Currently, he is a professor at the School of Computer Science and Technology, and AI Research Institute, Soochow University, and acts as the director of Department of Science, Technology and Industry in Soochow University, Suzhou. His research interests include natural language processing, information extraction, and embedded systems.

Guo-Dong Zhou received his Ph.D. degree in computer science from the National University of Singapore, Singapore, in 1999. Currently, he is a professor at the School of Computer Science and Technology, and AI Research Institute, Soochow University, Suzhou. His research interests include natural language processing, information extraction, and machine learning.

Electronic Supplementary Material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Qian, Z., Li, PF., Zhu, QM. et al. Document-Level Event Factuality Identification via Reinforced Semantic Learning Network. J. Comput. Sci. Technol. 39, 1248–1268 (2024). https://doi.org/10.1007/s11390-024-2655-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11390-024-2655-1

Keywords

Navigation