GDPNet: Refining Latent Multi-View Graph for Relation Extraction

Abstract

Relation Extraction (RE) is to predict the relation type of two entities that are mentioned in a piece of text, e.g., a sentence or a dialogue. When the given text is long, it is challenging to identify indicative words for the relation prediction. Recent advances on RE task are from BERT-based sequence modeling and graph-based modeling of relationships among the tokens in the sequence. In this paper, we propose to construct a latent multi-view graph to capture various possible relationships among tokens. We then refine this graph to select important words for relation prediction. Finally, the representation of the refined graph and the BERT-based sequence representation are concatenated for relation extraction. Specifically, in our proposed GDPNet (Gaussian Dynamic Time Warping Pooling Net), we utilize Gaussian Graph Generator (GGG) to generate edges of the multi-view graph. The graph is then refined by Dynamic Time Warping Pooling (DTWPool). On DialogRE and TACRED, we show that GDPNet achieves the best performance on dialogue-level RE, and comparable performance with the state-of-the-arts on sentence-level RE.

To appear at AAAI 2021

References in corpus (3)

• Self-Attention Graph Pooling
• Enriching Pre-trained Language Model with Entity Information for Relation Classification
• Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

Cited by in corpus (7)

• KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
• Ontology-enhanced Prompt-tuning for Few-shot Learning
• Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning
• An Embarrassingly Simple Model for Dialogue Relation Extraction
• Enhancing Low-Resource Relation Representations through Multi-View Decoupling
• Go Wider Instead of Deeper
• SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues