Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence
This work addresses fine-grained sentiment analysis for applications like review analysis, but it is incremental as it adapts an existing pre-trained model to a specific task.
The paper tackled aspect-based sentiment analysis by converting it into a sentence-pair classification task using auxiliary sentences, and fine-tuned BERT to achieve new state-of-the-art results on SentiHood and SemEval-2014 Task 4 datasets.
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.