从非结构化文本中提取关系三元组对于大规模知识图谱的构建至关重要。目前,大部分研究集中于从书面文本中抽取实体关系,从对话中抽取实体关系的研究还很少。和书面文本中的实体关系相比,对话中的实体关系更强调“人”的关系且更口语化。为此,该文提出了一种使用GCN(图卷积神经网络)建模对话情景的对话实体关系识别方法。该方法根据多人对话的特点,将对话句子看作节点,根据句子距离为句子间分配有权重的边,从而构建出一张对话情景图,然后使用GCN来建模对话之间的关系。在DialogRE数据集上的实验证明,该文方法优于本文研究同时期性能最好的模型。
Abstract
In contrast to the existing relation triple extraction focused on written texts, this paper proposes a GCN(Graph Convolutional Network) based approach to model dialogue scenarios. Compared with the entity relations in written text, those in dialogues emphasizes the relationship among humans and are more colloquial. To address this issue, our method regards dialogue sentences as nodes, and assigns weighted edges between sentences according to sentence distance. With such constructed a dialogue scene graph, we then applies GCN to model the relationship between dialogues. Experimental results on DialogRE show that our model outperforms the existing state-of-the-art baselines.
关键词
对话 /
关系抽取 /
图卷积神经网络
{{custom_keyword}} /
Key words
dialogue /
relation extraction /
graph convolutional network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] RIEDEL S, YAO L, MCCALLUM A. Modeling relations and their mentions without labeled text[C]//Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Berlin, Heidelberg, 2010: 148-163.
[2] GARDENT C,SHIMORINA A, NARAYAN S, et al. Creating training corpora for NLG micro-planning[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 179-188.
[3] YU D, SUN K,CARDIE C, et al. Dialogue-based relation extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020: 4927-4940.
[4] YAO Y, YE D, LI P, et al.DocRED: A large-scale document-level relation extraction dataset[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 764-777.
[5] SHI Z, HUANG M. A deep sequential model for discourse parsing on multi-party dialogues[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(01): 7007-7014.
[6] ZELENKO D,AONE C, RICHARDELLA A. Kernel methods for relation extraction[J]. Journal of Machine Learning Research, 2003, 3(2): 1083-1106.
[7] ZHOU G D,SU J, ZHANG J, et al. Exploring various knowledge in relation extraction[C]//Proceedings of the 43rd Annual Meeting of the Association for Computational linguistics, 2005: 427-434.
[8] MIWA M, BANSAL M. End-to-end relation extraction using LSTMs on sequences and tree structures[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016: 1105-1116.
[9] BEKOULIS G,DELEU J, DEMEESTER T, et al. Joint entity recognition and relation extraction as a multi-head selection problem[J]. Expert Systems with Applications, 2018, 114: 34-45.
[10] LI X, YIN F, SUN Z, et al. Entity-relation extraction as multi-turn question answering[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 1340-1350.
[11] WEI Z,SU J, WANG Y, et al. A novel cascade binary tagging framework for relational triple extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 1476-1488.
[12] MAJUMDER N,PORIA S, HAZARIKA D, et al. Dialoguernn: An attentive RNN for emotion detection in conversations[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(01): 6818-6825.
[13] ZHANG D, WU L, SUN C, et al. Modeling both context-and speaker-sensitive dependence for emotion detection in multi-speaker conversations[C]//Proceedings of the IJCAI, 2019: 5415-5421.
[14] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv: 1609.02907, 2016.
[15] LIU X, YOU X, ZHANG X, et al. Tensor graph convolutional networks for text classification[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, 2020: 8409-8416.
[16] GUI T, ZOU Y, ZHANG Q, et al. A lexicon-based graph neural network for Chinese NER[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 1039-1049.
[17] BASTINGS J,TITOV I, AZIZ W, et al. Graph convolutional encoders for syntax-aware neural machine translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017: 1957-1967.
[18] DEVLIN J, CHANG M W, LEE K, et al. BERT: Pretraining of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 4171-4186.
[19] HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[20] CHRISTOPOULOU F, MIWA M,ANANIADOU S. A Walk-based model on entity graphs for relation extraction[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 81-88.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(62276177,61836007)
{{custom_fund}}
PDF(1448 KB)
