SOTAVerified

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

2019-03-22NAACL 2019Code Available0· sign in to hype

Chi Sun, Luyao Huang, Xipeng Qiu

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
SemEval 2014 Task 4 Subtask 4BERT-pair-QA-BAccuracy (3-way)89.9Unverified
SentihoodBERT-pair-QA-BAspect87.9Unverified
SentihoodBERT-pair-QA-MAspect86.4Unverified

Reproductions