An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 504–515 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 504 An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis Ruidan He†‡, Wee Sun Lee†, Hwee Tou Ng†, and Daniel Dahlmeier‡ †Department of Computer Science, National University of Singapore ‡SAP Innovation Center Singapore †{ruidanhe,leews,nght}@comp.nus.edu.sg ‡d.dahlmeier@sap.com Abstract Aspect-based sentiment analysis produces a list of aspect terms and their corresponding sentiments for a natural language sentence. This task is usually done in a pipeline man- ner, with aspect term extraction performed first, followed by sentiment predictions to- ward the extracted aspect terms. While eas- ier to develop, such an approach does not fully exploit joint information from the two sub- tasks and does not use all available sources of training information that might be helpful, such as document-level labeled sentiment cor- pus. In this paper, we propose an interactive multi-task learning network (IMN) which is able to jointly learn multiple related tasks si- multaneously at both the token level as well as the document level. Unlike conventional multi-task learning methods that rely on learn- ing common features for the different tasks, IMN introduces a message passing architec- ture where information is iteratively passed to different tasks through a shared set of latent variables. Experimental results demonstrate superior performance of the proposed method against multiple baselines on three benchmark datasets. 1 Introduction Aspect-based sentiment analysis (ABSA) aims to determine people’s attitude towards specific as- pects in a review. This is done by extracting ex- plicit aspect mentions, referred to as aspect term extraction (AE), and detecting the sentiment ori- entation towards each extracted aspect term, re- ferred to as aspect-level sentiment classification (AS). For example, in the sentence “Great food but the service is dreadful”, the aspect terms are “food” and “service”, and the sentiment orienta- tions towards them are positive and negative re- spectively. In previous works, AE and AS are typically treated separately and the overall task is performed in a pipeline manner, which may not fully ex- ploit the joint information between the two tasks. Recently, two studies (Wang et al., 2018; Li et al., 2019) have shown that integrated models can achieve comparable results to pipeline meth- ods. Both works formulate the problem as a sin- gle sequence labeling task with a unified tagging scheme1. However, in their methods, the two tasks are only linked through unified tags, while the correlation between them is not explicitly mod- eled. Furthermore, the methods only learn from aspect-level instances, the size of which is usu- ally small, and do not exploit available informa- tion from other sources such as related document- level labeled sentiment corpora, which contain useful sentiment-related linguistic knowledge and are much easier to obtain in practice. In this work, we propose an interactive multi- task learning network (IMN), which solves both tasks simultaneously, enabling the interactions be- tween both tasks to be better exploited. Further- more, IMN allows AE and AS …

Content truncated to 500 words