Learning Unsupervised Semantic Document Representation for Fine-grained Aspect-based Sentiment Analysis.
Journal
SIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval
Pages
1105-1108
Date Issued
2019
Author(s)
Fu, Hao-Ming
Abstract
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. © 2019 Association for Computing Machinery.
Subjects
Document representation; Semantic learning; Sentence embedding; Sentiment analysis; Text classification; Unsupervised learning
Other Subjects
Classification (of information); Information retrieval; Large dataset; Sentiment analysis; Unsupervised learning; Document Representation; Fine grained; Large margins; On-machines; Semantic learning; Sentence embedding; State-of-the-art methods; Text classification; Information retrieval systems
Type
conference paper