Auxiliary Learning for Relation Extraction

doi:10.1109/TETCI.2020.3040444

Auxiliary Learning for Relation Extraction

2022-02-01

12

PRE

AI

DOI：10.1109/TETCI.2020.3040444

Original

Original request for help

Save

Abstract

En 中文

Relation extraction aims to predict a semantic relation between entities in a sentence, which is usually regarded as a classification problem. However, due to the limited relation set, many semantic relations are labeled as a special artificial relation type, termed no_relation, if they are beyond the predefined relation set. Existing methods treat this artificial relation type no_ relation as a common semantic relation without taking its rich semantics into account. In this paper, a novel auxiliary learning method is proposed to excavate the semantic information of no_relation, resulting in the improvement of generalization performance. The auxiliary learning method focuses on the model learning phase and introduces a binary classification task that treats the artificial relation type no_relation as negative class and the rest semantic types as positive class. The binary classification task, named auxiliary learning task, pays more attention to no_relation with a cost-sensitive loss by assigning higher cost on the misclassification of negative samples than positive ones. An additional reward is provided to the main prediction task by the auxiliary learning task, which leads to a better representation for relation extraction. Significant improvements are consistently achieved when state-of-the-art models are equipped with the auxiliary learning task on SemEval-2010 Task 8 and the large-scale TACRED. Especially, new state-of-the-art performance is achieved on SemEval-2010 Task 8 by the proposed method. Meanwhile, the motivation for introducing the auxiliary learning method is further reinforced by extensive experiments.

Keywords:

Auxiliary learning

dependency-based

neural networks

pretrained language models

relation extraction

sequence-based

Auxiliary Learning for Relation Extraction

Abstract

AI Summary

Journal

Organization