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

NAACL 2019  ·  Chi Sun, Luyao Huang, Xipeng Qiu ·

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. read more

PDF Abstract NAACL 2019 PDF NAACL 2019 Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Aspect Category Detection SemEval 2014 Task 4 Subtask 3 BERT-pair-NLI-B F1 score 92.18 # 1
Precision 93.57 # 1
Recall 90.83 # 1
Aspect-Based Sentiment Analysis SemEval 2014 Task 4 Subtask 4 BERT-pair-QA-B Accuracy (3-way) 89.9 # 1
Accuracy (4-way) 85.9 # 1
Binary Accuracy 95.6 # 1
Aspect-Based Sentiment Analysis Sentihood BERT-pair-QA-M Aspect 86.4 # 2
Sentiment 93.6 # 1
Aspect-Based Sentiment Analysis Sentihood BERT-pair-QA-B Aspect 87.9 # 1
Sentiment 93.3 # 2

Methods