Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6818–6830 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 6818 Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer Zeyu Li, Yilong Qin*, Zihan Liu*, and Wei Wang Department of Compute Science, University of California, Los Angeles {zyli,weiwang}@cs.ucla.edu {louisqin,zihanliu}@ucla.edu Abstract We study Comparative Preference Classifica- tion (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which entity is preferred over the other. High- quality CPC models can significantly ben- efit applications such as comparative ques- tion answering and review-based recommen- dation. Among the existing approaches, non- deep learning methods suffer from inferior per- formances. The state-of-the-art graph neural network-based ED-GAT (Ma et al., 2020) only considers syntactic information while ignoring the critical semantic relations and the senti- ments to the compared entities. We propose Sentiment Analysis Enhanced COmparative Network (SAECON) which improves CPC ac- curacy with a sentiment analyzer that learns sentiments to individual entities via domain adaptive knowledge transfer. Experiments on the CompSent-19 (Panchenko et al., 2019) dataset present a significant improvement on the F1 scores over the best existing CPC ap- proaches. 1 Introduction Comparative Preference Classification (CPC) is a natural language processing (NLP) task that pre- dicts whether a preference comparison exists be- tween two entities in a sentence and, if so, which entity wins the game. For example, given the sen- tence: Python is better suited for data analysis than MATLAB due to the many available deep learning libraries, a decisive comparison exists between Python and MATLAB and comparatively Python is preferred over MATLAB in the context. The CPC task can profoundly impact various real-world application scenarios. Search engine users may query not only factual questions but also comparative ones to meet their specific informa- tion needs (Gupta et al., 2017). Recommendation * These authors contributed equally. providers can analyze product reviews with com- parative statements to understand the advantages and disadvantages of the product comparing with similar ones. Several models have been proposed to solve this problem. Panchenko et al. (2019) first formalize the CPC problem, build and publish the CompSent-19 dataset, and experiment with numerous general ma- chine learning models such as Support Vector Ma- chine (SVM), representation-based classification, and XGBoost. However, these attempts consider CPC as a sentence classification while ignoring the semantics and the contexts of the entities (Ma et al., 2020). ED-GAT (Ma et al., 2020) marks the first entity- aware CPC approach that captures long-distance syntactic relations between the entities of interest by applying graph attention networks (GAT) to de- pendency parsing graphs. However, we argue that the disadvantages of such an approach are clear. Firstly, ED-GAT replaces the entity names with “entityA” and “entityB” for simplicity and hence deprives their semantics. Secondly, ED-GAT has a deep architecture with ten stacking GAT layers to tackle the long-distance issue between compared entities. However, more GAT layers result in a heavier computational workload and reduced train- …

Content truncated to 500 words