Deep Weighted MaxSAT for Aspect-based Opinion Extraction

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 5618–5628, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 5618 Deep Weighted MaxSAT for Aspect-based Opinion Extraction Meixi Wu∗ Wenya Wang Sinno Jialin Pan Nanyang Technological University, Singapore MWU008@e.ntu.edu.sg, {wangwy, sinnopan}@ntu.edu.sg Abstract Though deep learning has achieved significant success in various NLP tasks, most deep learn- ing models lack the capability of encoding ex- plicit domain knowledge to model complex causal relationships among different types of variables. On the other hand, logic rules offer a compact expression to represent the causal re- lationships to guide the training process. Logic programs can be cast as a satisfiability prob- lem which aims to find truth assignments to logic variables by maximizing the number of satisfiable clauses (MaxSAT). We adopt the MaxSAT semantics to model logic inference process and smoothly incorporate a weighted version of MaxSAT that connects deep neu- ral networks and a graphical model in a joint framework. The joint model feeds deep learn- ing outputs to a weighted MaxSAT layer to rectify the erroneous predictions and can be trained via end-to-end gradient descent. Our proposed model associates the benefits of high- level feature learning, knowledge reasoning, and structured learning with observable perfor- mance gain for the task of aspect-based opin- ion extraction. 1 Introduction Aspect-based opinion extraction aims to identify opinion targets (or aspects) of a review corpus that indicate specific product features, as well as the opinion terms expressed towards the aspects. For example, in the sentence “The wine list is excel- lent”, the aspect term is wine list, whereas the opin- ion term is excellent. Many deep learning mod- els have been proposed for this task via enumerat- ing high-level features (Liu et al., 2015; Xu et al., 2018a; Wang et al., 2017; Li and Lam, 2017; Yin et al., 2016; Wang et al., 2016). However, these methods fail to explicitly encode prior knowledge ∗ This work was done when the first author was an under- graduate student with Nanyang Technological University. on the relationships among aspect terms and opin- ion terms which are crucial for the task at hand, as shown in earlier rule-based models (Hu and Liu, 2004; Qiu et al., 2011). As in the previous example, if wine list is extracted as an aspect term and it has dependency relation “nsubj” with excellent which is an objective, then we can deduce that excellent is an opinion term. Though in (Yu et al., 2019), rules are incorporated as constraints into a deep neural network, the constraints cannot be backpropagated to the feature learning process. Recently, Wang and Pan (2020) proposed a joint model to com- bine deep learning with logic rules via minimizing the discrepancy between them. Their approach, however, only indirectly guides deep learning in training without the ability to rectify the predictions according to logic rules in inference. To address the aforementioned limitations for aspect-based opinion extraction, we propose a novel joint model DeepWMaxSAT to integrate logic knowledge via a weighted …

Content truncated to 500 words