Context-aware Embedding for Targeted Aspect-based Sentiment Analysis

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4678–4683 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 4678 Context-aware Embedding for Targeted Aspect-based Sentiment Analysis Bin Liang1, Jiachen Du1, Ruifeng Xu1∗, Binyang Li2, Hejiao Huang1 1Department of Computer Science, Harbin Institute of Technology (Shenzhen), China 2 School of Information Science and Technology, University of International Relations, Beijing, China 18b951033@stu.hit.edu.cn, dujiachen@stmail.hitsz.edu.cn xuruifeng@hit.edu.cn, byli@uir.edu.cn huanghejiao@hit.edu.cn Abstract Attention-based neural models were employed to detect the different aspects and sentiment polarities of the same target in targeted aspect- based sentiment analysis (TABSA). However, existing methods do not specifically pre-train reasonable embeddings for targets and aspects in TABSA. This may result in targets or as- pects having the same vector representations in different contexts and losing the context- dependent information. To address this prob- lem, we propose a novel method to refine the embeddings of targets and aspects. Such piv- otal embedding refinement utilizes a sparse co- efficient vector to adjust the embeddings of target and aspect from the context. Hence the embeddings of targets and aspects can be refined from the highly correlative words instead of using context-independent or ran- domly initialized vectors. Experiment results on two benchmark datasets show that our ap- proach yields the state-of-the-art performance in TABSA task. 1 Introduction Targeted aspect-based sentiment analysis (TABSA) aims at detecting aspects accord- ing to the specific target and inferring sentiment polarities corresponding to different target-aspect pairs simultaneously (Saeidi et al., 2016). For example, in sentence “location1 is your best bet for secure although expensive and location2 is too far.”, for target “location1”, the sentiment polarity is positive towards aspect “SAFETY” but is negative towards aspect “PRICE”. While “location2” only express negative polarity about aspect “TRANSIT-LOCATION”. This can be seen in Figure 1, e.g., where opinions on the aspects “SAFETY” and “PRICE” are expressed for target “location1” but not for target “location2”, whose ∗ Corresponding Author corresponding aspect is “TRANSIT-LOCATION ”. Here, an interesting phenomenon is that, the opinion “Positive” towards aspect “SAFETY” is expressed for target “location1” will be change if “location1” and “location2” are exchanged. That is to say, the representation of target and aspect should take full account of context in- formation rather than use context-independent representation. location1 is your best bet for secure although expensive and location2 is too far Target location1 Aspect SAFETY Sentiment Positive location1 PRICE Negative location2 TRANSIT Negative Figure 1: Example of TABSA task. Highly correlative words and corresponding aspects are in the same color. Entity names are masked by location1 and location2. Aspect-based sentiment analysis (ABSA) is a basic subtask of TABSA, which aims at inferring the sentiment polarities of different aspects in the sentence (Ruder et al., 2016; Chen et al., 2017; Gui et al., 2017; Peng et al., 2018; Ma et al., 2018a). Recently, attention-based neural models achieve remarkable success in ABSA (Fan et al., 2018; Wang et al., 2016; Tang et al., 2016). In TABSA task, the attention-based sentiment LSTM (Ma et …

Content truncated to 500 words