GDPNet: Refining Latent Multi-View Graph for Relation Extraction
TL
TL;DR
This paper proposes to construct a latent multi-view graph to capture various possible relationships among tokens and refined this graph to select important words for relation prediction, and shows that GDPNet achieves the best performance on dialogue-level RE, and comparable performance with the state-of-the-arts on sentence- level RE.
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. Our code is available at https://github.com/XueFuzhao/GDPNet.
References36 items
1
Attention-based bidirectional long short-term memory networks for extracting temporal relationships from clinical discharge summaries
2
Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning
3
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction
4
StructPool: Structured Graph Pooling via Conditional Random Fields
5