KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3198–3210 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 3198 KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis Deepanway Ghosal† , Devamanyu HazarikaΦ , Abhinaba Roy⊘, Navonil Majumder†, Rada Mihalcea⊓ , Soujanya Poria† †Singapore University of Technology and Design, Singapore ΦNational University of Singapore, Singapore ⊘Nanyang Technological University, Singapore ⊓University of Michigan, USA {deepanway ghosal@mymail., sporia@, nmder@}sutd.edu.sg, {hazarika@comp.nus, abhinaba.roy@ntu}.edu.sg, mihalcea@umich.edu Abstract Cross-domain sentiment analysis has received significant attention in recent years, prompted by the need to combat the domain gap between different applications that make use of senti- ment analysis. In this paper, we take a novel perspective on this task by exploring the role of external commonsense knowledge. We in- troduce a new framework, KinGDOM, which utilizes the ConceptNet knowledge graph to enrich the semantics of a document by provid- ing both domain-specific and domain-general background concepts. These concepts are learned by training a graph convolutional au- toencoder that leverages inter-domain con- cepts in a domain-invariant manner. Condi- tioning a popular domain-adversarial baseline method with these learned concepts helps im- prove its performance over state-of-the-art ap- proaches, demonstrating the efficacy of our proposed framework. 1 Introduction Sentiment Analysis (SA) is a popular NLP task used in many applications (Zhang et al., 2018). Current models trained for this task, however, can- not be reliably deployed due to the distributional mismatch between the training and evaluation do- mains (Daum´e III and Marcu, 2006). Domain adap- tation, a case of transductive transfer learning, is a widely studied field of research that can be ef- fectively used to tackle this problem (Wilson and Cook, 2018). Research in the field of cross-domain SA has pro- posed diverse approaches, which include learning domain-specific sentiment words/lexicons (Sarma et al., 2018; Hamilton et al., 2016b), co-occurrence based learning (Blitzer et al., 2007a), domain- adversarial learning (Ganin et al., 2016), among sketch Source domain: Books Target domain: Electronics TypeOf RelatedTo Review Documents wallpaper design Conceptnet Conceptual bridge source-specific domain-general target-specific Concepts: draw RelatedTo screen saver TypeOf Figure 1: ConceptNet provides networks with background concepts that enhance their semantic understanding. For ex- ample, for a target sentence from electronics domain, The software came with decent screen savers, comprising domain- specific terms like screen saver or wallpaper, ConceptNet helps connecting them to general concepts like design, thus allowing a network better understand their meaning. Further- more, inter-domain conceptual bridge can also be established to connect source and target domains (wallpaper–sketch have similar conceptual notions under the link design). others. In this work, we adopt the domain- adversarial framework and attempt to improve it further by infusing commonsense knowledge using ConceptNet – a large-scale knowledge graph (Speer et al., 2017). Augmenting neural models with external knowl- edge bases (KB) has shown benefits across a range of NLP applications (Peters et al., 2019; Li et al., 2019; IV et al., 2019; liu et al., 2019; Bi et al., 2019). Despite their popularity, efforts to incor- porate KBs into …

Content truncated to 500 words