Abstract
Event extraction plays an important role in natural language processing (NLP) applications, including question answering and information retrieval. Most of the previous state-of-the-art methods were lack of ability in capturing features in long range. Recent methods applied dependency tree via dependency-bridge and attention-based graph. However, most of the automatic processing tools used in those methods show poor performance on Chinese texts due to mismatching between word segmentation and labels, which results in error propagation. In this article, we propose a novel character-level Chinese event extraction framework via graph attention network (CAEE). We build our model upon the sequence labeling model, but enhance it with word information by incorporating the word lexicon into the character representations. We further exploit the inter-dependencies between event triggers and argument by building a word-character-based graph network via syntactic shortcut arcs with dependency-parsing. The architecture of the graph minimizes error propagation, which is the result of the error detection of the word boundaries in the processing of Chinese texts. To demonstrate the effectiveness of our work, we build a large-scale real-world corpus consisting of announcements of Chinese financial news without golden entities. Experiments on the corpus show that our approach achieves competitive results compared with previous work in the field of Chinese texts.
- [1] . 2020. Graph transformer for graph-to-sequence learning. In AAAI. 7464–7471.Google Scholar
- [2] . 2012. Joint modeling for Chinese event extraction with rich linguistic features. In COLING. 529–544.Google Scholar
- [3] . 2015. Event extraction via dynamic multi-pooling convolutional neural networks. In ACL. The Association for Computer Linguistics, 167–176.Google Scholar
- [4] . 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014).Google Scholar
- [5] . 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).Google Scholar
- [6] . 2019. A lexicon-based graph neural network for Chinese NER. In EMNLP-IJCNLP. 1039–1049.Google Scholar
- [7] . 1997. Long short-term memory. Neural Computat. 9, 8 (1997), 1735–1780. Google Scholar
Digital Library
- [8] . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- [9] . 2018. Analogical reasoning on Chinese morphological and semantic relations. In ACL. Association for Computational Linguistics, 138–143. Retrieved from http://aclweb.org/anthology/P18-2023.Google Scholar
- [10] . 2018. Nugget proposal networks for Chinese event detection. arXiv preprint arXiv:1805.00249 (2018).Google Scholar
- [11] . 2016. Leveraging FrameNet to improve automatic event detection. In ACL. The Association for Computer Linguistics.Google Scholar
- [12] . 2016. A probabilistic soft logic based approach to exploiting latent and global information in event classification. In AAAI. AAAI Press, 2993–2999. Google Scholar
Digital Library
- [13] . 2018. Jointly multiple events extraction via attention-based graph information aggregation. In EMNLP. Association for Computational Linguistics, 1247–1256.Google Scholar
- [14] . 2020. Simplify the usage of lexicon in Chinese NER. In ACL. Association for Computational Linguistics, 5951–5960.Google Scholar
- [15] . 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013).Google Scholar
- [16] . 2016. Joint event extraction via recurrent neural networks. In HLT-NAACL. The Association for Computational Linguistics, 300–309.Google Scholar
- [17] . 2015. Event detection and domain adaptation with convolutional neural networks. In ACL/IJCNLP. Association for Computational Linguistics, Beijing, China, 365–371.
DOI : https://doi.org/10.3115/v1/P15-2060Google Scholar - [18] . 2018. Jointly extracting event triggers and arguments by dependency-bridge RNN and tensor-based argument interaction. In AAAI. AAAI Press, 5916–5923. Google Scholar
Digital Library
- [19] . 2018. N-ary relation extraction using graph state LSTM. arXiv preprint arXiv:1808.09101 (2018).Google Scholar
- [20] . 2019. Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network. In EMNLP/IJCNLP. Association for Computational Linguistics, 3828–3838.Google Scholar
- [21] . 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- [22] . 2016. Joint extraction of events and entities within a document context. In HLT-NAACL. The Association for Computational Linguistics, 289–299.Google Scholar
- [23] . 2016. A convolution BiLSTM neural network model for Chinese event extraction. In Natural Language Understanding and Intelligent Applications. Springer, 275–287.Google Scholar
- [24] . 2020. A Practical Chinese Dependency Parser Based on a Large-scale Dataset.
arxiv:cs.CL/2009.00901 .Google Scholar - [25] . 2018. Chinese NER using lattice LSTM. In ACL. Association for Computational Linguistics, 1554–1564.Google Scholar
- [26] . 2019. Doc2EDAG: An end-to-end document-level framework for Chinese financial event extraction. In EMNLP/IJCNLP. Association for Computational Linguistics, 337–346.Google Scholar
Index Terms
Chinese Event Extraction via Graph Attention Network
Recommendations
Improving Chinese Character Representation with Formation Graph Attention Network
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementChinese characters are often composed of subcharacter components which are also semantically informative, and the component-level internal semantic features of a Chinese character inherently bring with additional information that benefits the semantic ...
Improving Event Extraction via Multimodal Integration
MM '17: Proceedings of the 25th ACM international conference on MultimediaIn this paper, we focus on improving Event Extraction (EE) by incorporating visual knowledge with words and phrases from text documents. We first discover visual patterns from large-scale text-image pairs in a weakly-supervised manner and then propose a ...
MABERT: Mask-Attention-Based BERT for Chinese Event Extraction
Event extraction is an essential but challenging task in information extraction. This task has considerably benefited from pre-trained language models, such as BERT. However, when it comes to the trigger-word mismatch problem in languages without natural ...






Comments