Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data

TL;DR

This paper introduces a multi-task learning approach that combines relation identification and classification with BIO tag embeddings to address class imbalance in relation extraction, significantly improving performance.

Contribution

It proposes a novel multi-task architecture that integrates BIO tag embeddings from NER to enhance relation extraction, especially under imbalanced data conditions.

Findings

Over 10% absolute increase in F1-score over baseline

Outperforms state-of-the-art on ACE 2005 Chinese and English datasets

BIO tag embeddings effectively improve relation extraction models

Abstract

In practical scenario, relation extraction needs to first identify entity pairs that have relation and then assign a correct relation class. However, the number of non-relation entity pairs in context (negative instances) usually far exceeds the others (positive instances), which negatively affects a model's performance. To mitigate this problem, we propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss. Meanwhile, we observe that a sentence may have multiple entities and relation mentions, and the patterns in which the entities appear in a sentence may contain useful semantic information that can be utilized to distinguish between positive and negative instances. Thus we further incorporate the embeddings of character-wise/word-wise BIO tag from the named entity recognition task into character/word embeddings to enrich the input representation. Experiment results show that our proposed approach can significantly improve the performance of a baseline model with more than 10% absolute increase in F1-score, and outperform the state-of-the-art models on ACE 2005 Chinese and English corpus. Moreover, BIO tag embeddings are particularly effective and can be used to improve other models as well.