InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction
This work provides an incremental improvement for researchers and practitioners working on distantly-supervised relation extraction by demonstrating the utility of additional information sources.
This paper addresses the sparse and noisy bag issues in distantly-supervised relation extraction by incorporating entity descriptions and multi-grained entity types as additional information sources. It proposes an end-to-end multi-view learning framework, InSRL, which jointly learns representations from these sources and uses inner-view and cross-view attention mechanisms to improve performance on a popular benchmark dataset.
Distant supervision makes it possible to automatically label bags of sentences for relation extraction by leveraging knowledge bases, but suffers from the sparse and noisy bag issues. Additional information sources are urgently needed to supplement the training data and overcome these issues. In this paper, we introduce two widely-existing sources in knowledge bases, namely entity descriptions, and multi-grained entity types to enrich the distantly supervised data. We see information sources as multiple views and fusing them to construct an intact space with sufficient information. An end-to-end multi-view learning framework is proposed for relation extraction via Intact Space Representation Learning (InSRL), and the representations of single views are jointly learned simultaneously. Moreover, inner-view and cross-view attention mechanisms are used to highlight important information on different levels on an entity-pair basis. The experimental results on a popular benchmark dataset demonstrate the necessity of additional information sources and the effectiveness of our framework. We will release the implementation of our model and dataset with multiple information sources after the anonymized review phase.