Hybrid Attention-Based Transformer Block Model for Distant Supervision Relation Extraction

TL;DR

This paper introduces a hybrid attention-based Transformer model combined with multi-instance learning to improve distant supervision relation extraction, effectively reducing wrong labels and outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a novel Transformer-based framework with sentence-level attention for DSRE, enhancing relation extraction accuracy by addressing label noise.

Findings

Outperforms state-of-the-art algorithms on NYT dataset

Effectively captures syntactic and semantic features of sentences

Reduces wrong labeling issues in distant supervision

Abstract

With an exponential explosive growth of various digital text information, it is challenging to efficiently obtain specific knowledge from massive unstructured text information. As one basic task for natural language processing (NLP), relation extraction aims to extract the semantic relation between entity pairs based on the given text. To avoid manual labeling of datasets, distant supervision relation extraction (DSRE) has been widely used, aiming to utilize knowledge base to automatically annotate datasets. Unfortunately, this method heavily suffers from wrong labelling due to the underlying strong assumptions. To address this issue, we propose a new framework using hybrid attention-based Transformer block with multi-instance learning to perform the DSRE task. More specifically, the Transformer block is firstly used as the sentence encoder to capture syntactic information of sentences, which mainly utilizes multi-head self-attention to extract features from word level. Then, a more concise sentence-level attention mechanism is adopted to constitute the bag representation, aiming to incorporate valid information of each sentence to effectively represent the bag. Experimental results on the public dataset New York Times (NYT) demonstrate that the proposed approach can outperform the state-of-the-art algorithms on the evaluation dataset, which verifies the effectiveness of our model for the DSRE task.