Transformer-based Multi-Aspect Modeling for Multi-Aspect Multi-Sentiment Analysis

TL;DR

This paper introduces a Transformer-based model for multi-aspect multi-sentiment analysis, effectively capturing relations between aspects and improving sentiment detection accuracy on a challenging new dataset.

Contribution

It proposes a novel Transformer-based Multi-aspect Modeling scheme that advances multi-aspect sentiment analysis by handling complex sentences with multiple aspects and sentiments.

Findings

Achieves significant improvements over BERT and RoBERTa baselines.

Ranks 2nd in NLPCC 2020 Shared Task 2.

Effectively models relations between multiple aspects in sentences.

Abstract

Aspect-based sentiment analysis (ABSA) aims at analyzing the sentiment of a given aspect in a sentence. Recently, neural network-based methods have achieved promising results in existing ABSA datasets. However, these datasets tend to degenerate to sentence-level sentiment analysis because most sentences contain only one aspect or multiple aspects with the same sentiment polarity. To facilitate the research of ABSA, NLPCC 2020 Shared Task 2 releases a new large-scale Multi-Aspect Multi-Sentiment (MAMS) dataset. In the MAMS dataset, each sentence contains at least two different aspects with different sentiment polarities, which makes ABSA more complex and challenging. To address the challenging dataset, we re-formalize ABSA as a problem of multi-aspect sentiment analysis, and propose a novel Transformer-based Multi-aspect Modeling scheme (TMM), which can capture potential relations between multiple aspects and simultaneously detect the sentiment of all aspects in a sentence. Experiment results on the MAMS dataset show that our method achieves noticeable improvements compared with strong baselines such as BERT and RoBERTa, and finally ranks the 2nd in NLPCC 2020 Shared Task 2 Evaluation.