Learning Unsupervised Semantic Document Representation for Fine-grained Aspect-based Sentiment Analysis
This work addresses the challenge of document representation for sentiment analysis, which is crucial for NLP applications, but it appears incremental as it builds upon existing families of methods.
The paper tackled the problem of learning unsupervised semantic document representations for fine-grained aspect-based sentiment analysis, proposing a model that overcomes weaknesses in existing sequential and non-sequential methods, and it outperformed state-of-the-art methods on popular datasets by a large margin.
Document representation is the core of many NLP tasks on machine understanding. A general representation learned in an unsupervised manner reserves generality and can be used for various applications. In practice, sentiment analysis (SA) has been a challenging task that is regarded to be deeply semantic-related and is often used to assess general representations. Existing methods on unsupervised document representation learning can be separated into two families: sequential ones, which explicitly take the ordering of words into consideration, and non-sequential ones, which do not explicitly do so. However, both of them suffer from their own weaknesses. In this paper, we propose a model that overcomes difficulties encountered by both families of methods. Experiments show that our model outperforms state-of-the-art methods on popular SA datasets and a fine-grained aspect-based SA by a large margin.