Heterogeneous Reinforcement Learning Network for Aspect-Based Sentiment Classification With External Knowledge
Yukun Cao, Yijia Tang, Haizhou Du, Feifei Xu, Ziyue Wei, Chengkun Jin
Abstract
Aspect-based sentiment classification aims to automatically predict the sentiment polarity of the specific aspect in a text. However, it is challenging to confirm the mapping between the aspect and the core context since a number of existing methods concentrate on building the global relations of the full context rather than the partial connections based on the aspects. Motivated by the fundamental insights of reinforcement learning, we propose a novel <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>H</b></u> eterogeneous <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>R</b></u> einforcement <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>L</b></u> earning <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>N</b></u> etwork for aspect-based sentiment analysis (HRLN) to alleviate these issues, which contains two primary components, a heterogeneous network module, and a knowledge graph-based reinforcement learning module consistent with common-sense knowledge and emotional knowledge. To evaluate the effectiveness of HRLN, we conduct extensive experiments on five benchmark datasets, which indicate that HRLN achieves competitive performance and yields state-of-the-art results on all datasets. Additionally, we present an intuitive comprehension of why our HRLN model is more robust for aspect-based sentiment classification via case studies.