Enhancing BERT Representation With Context-Aware Embedding for Aspect-Based Sentiment Analysis

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Xinglong LI
  • Xingyu FU
  • Guangluan XU
  • Yang YANG
  • Li JIN
  • Qing LIU
  • Tianyuan XIANG

Detail(s)

Original languageEnglish
Pages (from-to)46868-46876
Journal / PublicationIEEE Access
Volume8
Online published5 Mar 2020
Publication statusPublished - 2020
Externally publishedYes

Link(s)

Abstract

Aspect-based sentiment analysis, which aims to predict the sentiment polarities for the given aspects or targets, is a broad-spectrum and challenging research area. Recently, pre-trained models, such as BERT, have been used in aspect-based sentiment analysis. This fine-grained task needs auxiliary information to distinguish each aspect. But the input form of BERT is only a words sequence which can not provide extra contextual information. To address this problem, we introduce a new method named GBCN which uses a gating mechanism with context-aware aspect embeddings to enhance and control the BERT representation for aspect-based sentiment analysis. Firstly, the input texts are fed into BERT and context-aware embedding layer to generate BERT representation and refined context-aware embeddings separately. These refined embeddings contain the most correlated information selected in the context. Then, we employ a gating mechanism to control the propagation of sentiment features from BERT output with context-aware embeddings. The experiments of our model obtain new state-of-the-art results on the SentiHood and SemEval-2014 datasets, achieving a test F1 of 88.0 and 92.9 respectively.

Research Area(s)

  • Aspect-based sentiment analysis, BERT network, context-aware embedding

Citation Format(s)

Enhancing BERT Representation With Context-Aware Embedding for Aspect-Based Sentiment Analysis. / LI, Xinglong; FU, Xingyu; XU, Guangluan; YANG, Yang; WANG, Jiuniu; JIN, Li; LIU, Qing; XIANG, Tianyuan.

In: IEEE Access, Vol. 8, 2020, p. 46868-46876.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

Download Statistics

No data available