Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
113 tokens/sec
GPT-4o
12 tokens/sec
Gemini 2.5 Pro Pro
24 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
3 tokens/sec
DeepSeek R1 via Azure Pro
33 tokens/sec
2000 character limit reached

Adaptive Ordered Information Extraction with Deep Reinforcement Learning (2306.10787v1)

Published 19 Jun 2023 in cs.CL

Abstract: Information extraction (IE) has been studied extensively. The existing methods always follow a fixed extraction order for complex IE tasks with multiple elements to be extracted in one instance such as event extraction. However, we conduct experiments on several complex IE datasets and observe that different extraction orders can significantly affect the extraction results for a great portion of instances, and the ratio of sentences that are sensitive to extraction orders increases dramatically with the complexity of the IE task. Therefore, this paper proposes a novel adaptive ordered IE paradigm to find the optimal element extraction order for different instances, so as to achieve the best extraction results. We also propose an reinforcement learning (RL) based framework to generate optimal extraction order for each instance dynamically. Additionally, we propose a co-training framework adapted to RL to mitigate the exposure bias during the extractor training phase. Extensive experiments conducted on several public datasets demonstrate that our proposed method can beat previous methods and effectively improve the performance of various IE tasks, especially for complex ones.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Pere-Lluís Huguet Cabot and Roberto Navigli. 2021. Rebel: Relation extraction by end-to-end language generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2370–2381.
  2. Hacred: A large-scale relation extraction dataset toward hard cases in practical applications. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2819–2831.
  3. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  4. Template filling with generative transformers. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 909–914.
  5. Reinforcement learning for relation classification from noisy data. In Proceedings of the aaai conference on artificial intelligence, volume 32.
  6. Ralph Grishman. 2019. Twenty-five years of information extraction. Natural Language Engineering, 25(6):677–692.
  7. An overview of event extraction from text. DeRiVE@ ISWC, pages 48–57.
  8. Degree: A data-efficient generation-based event extraction model. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1890–1908.
  9. Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451.
  10. A survey on deep learning for named entity recognition. IEEE Transactions on Knowledge and Data Engineering, 34(1):50–70.
  11. Duie: A large-scale chinese dataset for information extraction. In CCF International Conference on Natural Language Processing and Chinese Computing, pages 791–800. Springer.
  12. Tdeer: An efficient translating decoding schema for joint extraction of entities and relations. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8055–8064.
  13. Duee: a large-scale dataset for chinese event extraction in real-world scenarios. In CCF International Conference on Natural Language Processing and Chinese Computing, pages 534–545. Springer.
  14. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
  15. Unified structure generation for universal information extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5755–5772.
  16. A general framework for information extraction using dynamic span graphs. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3036–3046.
  17. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602.
  18. Human-level control through deep reinforcement learning. nature, 518(7540):529–533.
  19. David Nadeau and Satoshi Sekine. 2007. A survey of named entity recognition and classification. Lingvisticae Investigationes, 30(1):3–26.
  20. Improving information extraction by acquiring external evidence with reinforcement learning. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2355–2365.
  21. Relation extraction: A survey. arXiv preprint arXiv:1712.05191.
  22. 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.
  23. Modeling relations and their mentions without labeled text. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 148–163. Springer.
  24. Prioritized experience replay. arXiv preprint arXiv:1511.05952.
  25. Onerel: Joint entity and relation extraction with one module in one step. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 11285–11293.
  26. Casee: A joint learning framework with cascade decoding for overlapping event extraction. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 164–174.
  27. Global pointer: Novel efficient span-based approach for named entity recognition. arXiv preprint arXiv:2208.03054.
  28. A hierarchical framework for relation extraction with reinforcement learning. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 7072–7079.
  29. Action branching architectures for deep reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32.
  30. Deep reinforcement learning with double q-learning. In Proceedings of the AAAI conference on artificial intelligence, volume 30.
  31. Entity, relation, and event extraction with contextualized span representations. 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 5784–5789.
  32. Jianing Wang. 2020. Rh-net: Improving neural relation extraction via reinforcement learning and hierarchical relational searching. arXiv preprint arXiv:2010.14255.
  33. Tplinker: Single-stage joint extraction of entities and relations through token pair linking. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1572–1582.
  34. A novel cascade binary tagging framework for relational triple extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1476–1488.
  35. Revisiting the negative data of distantly supervised relation extraction. 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 3572–3581.
  36. Document-level event extraction via heterogeneous graph-based interaction model with a tracker. 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 3533–3546.
  37. Dcfee: A document-level chinese financial event extraction system based on automatically labeled training data. In Proceedings of ACL 2018, System Demonstrations, pages 50–55.
  38. Exploring pre-trained language models for event extraction and generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5284–5294.
  39. Contrastive triple extraction with generative transformer. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 14257–14265.
  40. Learning the extraction order of multiple relational facts in a sentence with reinforcement learning. 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 367–377.
  41. 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), pages 506–514.
  42. Doc2edag: An end-to-end document-level framework for chinese financial event extraction. 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 337–346.
  43. Joint extraction of entities and relations based on a novel tagging scheme. arXiv preprint arXiv:1706.05075.
  44. Efficient document-level event extraction via pseudo-trigger-aware pruned complete graph. arXiv preprint arXiv:2112.06013.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now