Abstract
Recently, character information has been successfully introduced into the encoder-decoder event detection model to relieve the trigger-word mismatch problem, thus achieving impressive results in the languages without natural delimiters (i.e., Chinese). However, it is introduced into the encoder or the decoder separately, which makes the advantage of character information not be captured and represented adequately for event detection. In this article, we proposed a novel method to model character information in both the encoding and decoding stages to advance the neural event detection model. In particular, the proposed method can encode both words and characters and predict their event types jointly and further leverage interactions between word and its characters to optimize the inference. Experimental results show that the proposed model outperforms previous event detection methods on the ACE2005 Chinese benchmark. We release our code at Github.1
- [1] . 2017. Fast and accurate neural word segmentation for chinese. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 608–615.Google Scholar
Cross Ref
- [2] . 2012. Joint modeling for chinese event extraction with rich linguistic features. In Proceedings of the International Conference on Computational Linguistics (COLING’12). 529–544.Google Scholar
- [3] . 2015. Event extraction via dynamic multi-pooling convolutional neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, 167–176.Google Scholar
Cross Ref
- [4] . 2020. Revisiting pre-trained models for Chinese natural language processing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing: Findings. Association for Computational Linguistics, 657–668.Google Scholar
Cross Ref
- [5] . 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, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171–4186.Google Scholar
- [6] . 2019. Event detection with trigger-aware lattice neural network. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 347–356.Google Scholar
Cross Ref
- [7] . 2016. A language-independent neural network for event detection. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, 66–71.Google Scholar
Cross Ref
- [8] . 2011. Using cross-entity inference to improve event extraction. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 1127–1136. Google Scholar
Digital Library
- [9] . 2016. Neural architectures for named entity recognition. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, 260–270.Google Scholar
Cross Ref
- [10] . 2012. Employing compositional semantics and discourse consistency in Chinese event extraction. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics, 1006–1016. Google Scholar
Digital Library
- [11] . 2012. Joint modeling of trigger identification and event type determination in Chinese event extraction. In Proceedings of the 24th International Conference on Computational Linguistics. Association for Computational Linguistics, 1635–1652.Google Scholar
- [12] . 2013. Joint event extraction via structured prediction with global features. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 73–82. https://www.aclweb.org/anthology/P13-1008.Google Scholar
- [13] . 2018. Analogical reasoning on chinese morphological and semantic relations. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 138–143.Google Scholar
Cross Ref
- [14] . 2010. Using document level cross-event inference to improve event extraction. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 789–797. Google Scholar
Digital Library
- [15] . 2018. Adaptive scaling for sparse detection in information extraction. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 1033–1043.Google Scholar
Cross Ref
- [16] . 2018. Nugget proposal networks for Chinese event detection. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 1565–1574.Google Scholar
Cross Ref
- [17] . 2018. Jointly multiple events extraction via attention-based graph information aggregation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 1247–1256.Google Scholar
Cross Ref
- [18] . 2002. Branch-and-cut algorithms for combinatorial optimization problems. Handbook of Applied Optimization, vol. 1. Oxford University Press, Oxford, UK, 65–77.Google Scholar
- [19] . 2018. Graph convolutional networks with argument-aware pooling for event detection. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32. Google Scholar
Digital Library
- [20] . 2015. Event detection and domain adaptation with convolutional neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). Association for Computational Linguistics, 365–371.Google Scholar
Cross Ref
- [21] . 2020. Detecting entities of works for chinese chatbot. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 19, 6, Article
88 (Sept. 2020), 13 pages. Google ScholarDigital Library
- [22] . 2021. Document-Level relation extraction with reconstruction. Proc. AAAI Conf. Artif. Intelli. 35, 16 (
May 2021), 14167–14175.Google Scholar - [23] . 2017. Leveraging knowledge bases in LSTMs for improving machine reading. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 1436–1446.Google Scholar
Cross Ref
- [24] . 2018. NCRF++: An open-source neural sequence labeling toolkit. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics.Google Scholar
Cross Ref
- [25] . 2012. ADADELTA: An adaptive learning rate method. Computing Research Repository abs/1212.5701. http://arxiv.org/abs/1212.5701.Google Scholar
- [26] . 2016. A convolution BiLSTM neural network model for chinese event extraction. In Natural Language Understanding and Intelligent Applications. Springer International Publishing, 275–287. Google Scholar
- [27] . 2018. Chinese NER using lattice LSTM. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 1554–1564.Google Scholar
Cross Ref
- [28] . 2010. A unified character-based tagging framework for chinese word segmentation. ACM Trans. Asian Lang. Inf. Process. 9, 2, Article
5 (June 2010), 32 pages. Google ScholarDigital Library
Index Terms
Advancing Chinese Event Detection via Revisiting Character Information
Recommendations
Chinese-Japanese cross language information retrieval: a Han character based approach
WWSM '00: Proceedings of the ACL-2000 workshop on Word senses and multi-linguality - Volume 8In this paper, we investigate cross language information retrieval (CLIR) for Chinese and Japanese texts utilizing the Han characters - common ideographs used in writing Chinese, Japanese and Korean (CJK) languages. The Unicode encoding scheme, which ...
Solving Chinese Character Puzzles Based on Character Strokes
Natural Language Processing and Chinese ComputingAbstractChinese character puzzles are popular games in China. To solve a character puzzle, people need to fully consider the meaning and the strokes of each character in puzzles. Therefore, Chinese character puzzles are complicated and it can be a ...
Chinese-Japanese cross language information retrieval: a Han character based approach
WorkSense '00: Proceedings of the ACL-2000 Workshop on Word Senses and Multi-LingualityIn this paper, we investigate cross language information retrieval (CLIR) for Chinese and Japanese texts utilizing the Han characters -- common ideographs used in writing Chinese, Japanese and Korean (CJK) languages. The Unicode encoding scheme, which ...






Comments