DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis

This paper focuses on learning domainoriented language models driven by end tasks, which aims to combine the worlds of both general-purpose language models (such as ELMo and BERT) and domain-specific language understanding. We propose DomBERT, an extension of BERT to learn from both indomain corpus and relevant domain corpora. This helps in learning domain language models with low-resources. Experiments are conducted on an assortment of tasks in aspectbased sentiment analysis (ABSA), demonstrating promising results. 1