Boundaries and edges rethinking: An end-to-end neural model for overlapping entity relation extraction

Abstract Overlapping entity relation extraction has received extensive research attention in recent years. However, existing methods suffer from the limitation of long-distance dependencies between entities, and fail to extract the relations when the overlapping situation is relatively complex. This issue limits the performance of the task. In this paper, we propose an end-to-end neural model for overlapping relation extraction by treating the task as a quintuple prediction problem. The proposed method first constructs the entity graphs by enumerating possible candidate spans, then models the relational graphs between entities via a graph attention model. Experimental results on five benchmark datasets show that the proposed model achieves the current best performance, outperforming previous methods and baseline systems by a large margin. Further analysis shows that our model can effectively capture the long-distance dependencies between entities in a long sentence.

[1]  Bo Xu,et al.  Joint entity and relation extraction based on a hybrid neural network , 2017, Neurocomputing.

[2]  Satoshi Sekine,et al.  A survey of named entity recognition and classification , 2007 .

[3]  Thomas Demeester,et al.  An attentive neural architecture for joint segmentation and parsing and its application to real estate ads , 2017, Expert Syst. Appl..

[4]  Donghong Ji,et al.  Drug-Drug Interaction Extraction Using a Span-based Neural Network Model , 2019, 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[5]  Yaser Al-Onaizan,et al.  Span-Level Model for Relation Extraction , 2019, ACL.

[6]  Chaogang Fu,et al.  Tracking user-role evolution via topic modeling in community question answering , 2019, Inf. Process. Manag..

[7]  Thomas Demeester,et al.  Adversarial training for multi-context joint entity and relation extraction , 2018, EMNLP.

[8]  Chris Develder,et al.  Joint entity recognition and relation extraction as a multi-head selection problem , 2018, Expert Syst. Appl..

[9]  Guangchun Luo,et al.  Direction-sensitive relation extraction using Bi-SDP attention model , 2020, Knowl. Based Syst..

[10]  Donghong Ji,et al.  Dispatched attention with multi-task learning for nested mention recognition , 2020, Inf. Sci..

[11]  Yue Zhang,et al.  End-to-End Neural Relation Extraction with Global Optimization , 2017, EMNLP.

[12]  Rajarshi Das,et al.  Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks , 2017, ACL.

[13]  Ebrahim Bagheri,et al.  Feature-enriched matrix factorization for relation extraction , 2019, Inf. Process. Manag..

[14]  Makoto Miwa,et al.  Modeling Joint Entity and Relation Extraction with Table Representation , 2014, EMNLP.

[15]  Shi Feng,et al.  Knowledge-Based Semantic Embedding for Machine Translation , 2016, ACL.

[16]  Jian Su,et al.  Exploring Various Knowledge in Relation Extraction , 2005, ACL.

[17]  Zhi Jin,et al.  Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths , 2015, EMNLP.

[18]  Jun Zhao,et al.  Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism , 2018, ACL.

[19]  Diego Marcheggiani,et al.  Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling , 2017, EMNLP.

[20]  Guillaume Lample,et al.  Neural Architectures for Named Entity Recognition , 2016, NAACL.

[21]  Mari Ostendorf,et al.  Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction , 2018, EMNLP.

[22]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[23]  Mari Ostendorf,et al.  A general framework for information extraction using dynamic span graphs , 2019, NAACL.

[24]  Heng Ji,et al.  CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases , 2016, WWW.

[25]  Dan Roth,et al.  A Linear Programming Formulation for Global Inference in Natural Language Tasks , 2004, CoNLL.

[26]  Claire Cardie,et al.  Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees , 2017, ACL.

[27]  Fei Li,et al.  A neural joint model for entity and relation extraction from biomedical text , 2017, BMC Bioinformatics.

[28]  Karima Meftouh,et al.  Machine translation for Arabic dialects (survey) , 2017, Inf. Process. Manag..

[29]  Zhiyuan Liu,et al.  Neural Knowledge Acquisition via Mutual Attention Between Knowledge Graph and Text , 2018, AAAI.

[30]  Wei-Yun Ma,et al.  GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction , 2019, ACL.

[31]  Qianli Ma,et al.  Relation Classification via Keyword-Attentive Sentence Mechanism and Synthetic Stimulation Loss , 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[32]  Baogang Wei,et al.  Knowledge representation learning with entity descriptions, hierarchical types, and textual relations , 2019, Inf. Process. Manag..

[33]  Makoto Miwa,et al.  End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures , 2016, ACL.

[34]  Ashish Vaswani,et al.  Supertagging With LSTMs , 2016, NAACL.

[35]  Yue Zhang,et al.  Joint Extraction of Entities and Relations Based on a Novel Graph Scheme , 2018, IJCAI.