Gated Convolutional Neural Networks with Sentence-Related Selection for Distantly Supervised Relation Extraction

Yufeng CHEN  Siqi LI  Xingya LI  Jinan XU  Jian LIU  

IEICE TRANSACTIONS on Information and Systems   Vol.E104-D   No.9   pp.1486-1495
Publication Date: 2021/09/01
Publicized: 2021/06/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2020EDP7249
Type of Manuscript: PAPER
Category: Natural Language Processing
relation extraction,  distant supervision,  gated convolutional neural networks,  multi-head self-attention,  soft-label,  sentence-related selection,  

Full Text: PDF(2.3MB)>>
Buy this Article

Relation extraction is one of the key basic tasks in natural language processing in which distant supervision is widely used for obtaining large-scale labeled data without expensive labor cost. However, the automatically generated data contains massive noise because of the wrong labeling problem in distant supervision. To address this problem, the existing research work mainly focuses on removing sentence-level noise with various sentence selection strategies, which however could be incompetent for disposing word-level noise. In this paper, we propose a novel neural framework considering both intra-sentence and inter-sentence relevance to deal with word-level and sentence-level noise from distant supervision, which is denoted as Sentence-Related Gated Piecewise Convolutional Neural Networks (SR-GPCNN). Specifically, 1) a gate mechanism with multi-head self-attention is adopted to reduce word-level noise inside sentences; 2) a soft-label strategy is utilized to alleviate wrong-labeling propagation problem; and 3) a sentence-related selection model is designed to filter sentence-level noise further. The extensive experimental results on NYT dataset demonstrate that our approach filters word-level and sentence-level noise effectively, thus significantly outperforms all the baseline models in terms of both AUC and top-n precision metrics.