papers AI Learner
The Github is limit! Click to go to the new site.

Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence

2019-03-22
Chi Sun, Luyao Huang, Xipeng Qiu

Abstract

Aspect-based sentiment analysis (ABSA), which aims to identify fine-grained opinion polarity towards a specific aspect, is a challenging subtask of sentiment analysis (SA). In this paper, we construct an auxiliary sentence from the aspect and convert ABSA to a sentence-pair classification task, such as question answering (QA) and natural language inference (NLI). We fine-tune the pre-trained model from BERT and achieve new state-of-the-art results on SentiHood and SemEval-2014 Task 4 datasets.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.09588

PDF

http://arxiv.org/pdf/1903.09588


Similar Posts

Comments