Aspect Term Extraction with History Attention and Selective Transformation

Abstract

Aspect Term Extraction (ATE), a key sub-task in Aspect-Based Sentiment Analysis, aims to extract explicit aspect expressions from online user reviews. We present a new framework for tackling ATE. It can exploit two useful clues, namely opinion summary and aspect detection history. Opinion summary is distilled from the whole input sentence, conditioned on each current token for aspect prediction, and thus the tailor-made summary can help aspect prediction on this token. Another clue is the information of aspect detection history, and it is distilled from the previous aspect predictions so as to leverage the coordinate structure and tagging schema constraints to upgrade the aspect prediction. Experimental results over four benchmark datasets clearly demonstrate that our framework can outperform all state-of-the-art methods.

arXiv commentIJCAI 2018

References in corpus (2)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Effective Approaches to Attention-based Neural Machine Translation

Cited by in corpus (6)

• A Unified Model for Opinion Target Extraction and Target Sentiment Prediction
• First Target and Opinion then Polarity: Enhancing Target-opinion Correlation for Aspect Sentiment Triplet Extraction
• Position-Aware Tagging for Aspect Sentiment Triplet Extraction
• Controlled CNN-based Sequence Labeling for Aspect Extraction
• Aspect-Sentiment-Multiple-Opinion Triplet Extraction
• Exploring Conditional Text Generation for Aspect-Based Sentiment Analysis