论文标题
GDPNET：用于关系提取的潜在多视图图
GDPNet: Refining Latent Multi-View Graph for Relation Extraction
论文作者
论文摘要
关系提取（re）是为了预测文本中提到的两个实体的关系类型，例如句子或对话。当给定的文本长时间时，确定关系预测的指示词是一个挑战。 RE任务的最新进展来自基于BERT的序列建模和基于图的基于图形的关系模型。在本文中，我们建议构建一个潜在的多视图图，以捕获令牌之间的各种可能的关系。然后，我们完善此图以选择重要词以进行关系预测。最后，将精制图和基于BERT的序列表示的表示是为了提取关系提取。具体而言，在我们提出的GDPNET（高斯动态时间翘曲池网）中，我们利用高斯图生成器（GGG）生成多视图图的边缘。然后通过动态时间扭曲池（DTWPool）来完善图表。在Dialogre和Tacred中，我们表明GDPNET在对话级别的RE上取得了最佳性能，并且与句子级别的最先进的RE相当的性能。
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.
