Aspect Term Extraction with History Attention and Selective Transformation

TL;DR

This paper introduces a novel framework for Aspect Term Extraction that leverages opinion summaries and detection history, significantly improving accuracy over existing methods in multiple benchmark datasets.

Contribution

The proposed framework uniquely combines opinion summaries and detection history with selective transformation to enhance aspect prediction accuracy.

Findings

Outperforms all state-of-the-art methods on four benchmark datasets

Effectively utilizes opinion summaries conditioned on each token

Leverages detection history to incorporate structural and schema constraints

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.