Enhancing BERT Representation With Context-Aware Embedding for Aspect-Based Sentiment Analysis
Lists
Only you see this
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.
BibTeX
@article{li2020enhancing,
author = {Xinlong Li and Xingyu Fu and Guangluan Xu and Yang Yang and Jiuniu Wang and Li Jin and Qing Liu and Tianyuan Xiang},
title = {{Enhancing BERT Representation With Context-Aware Embedding for Aspect-Based Sentiment Analysis}},
journal = {IEEE Access},
year = {2020},
doi = {10.1109/access.2020.2978511},
}Loading related content...