Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets

TL;DR

This paper presents an unsupervised aspect term extraction method using B-LSTM and CRF, leveraging automatically labeled datasets to outperform supervised baselines in sentiment analysis tasks.

Contribution

It introduces a novel architecture for ATE that can be used unsupervised and a method to automatically generate labeled datasets for training.

Findings

Achieves top-ranking performance in supervised ATE

Automatically labeled datasets improve unsupervised ATE accuracy

Outperforms SemEval ABSA baseline with high precision

Abstract

Aspect Term Extraction (ATE) identifies opinionated aspect terms in texts and is one of the tasks in the SemEval Aspect Based Sentiment Analysis (ABSA) contest. The small amount of available datasets for supervised ATE and the costly human annotation for aspect term labelling give rise to the need for unsupervised ATE. In this paper, we introduce an architecture that achieves top-ranking performance for supervised ATE. Moreover, it can be used efficiently as feature extractor and classifier for unsupervised ATE. Our second contribution is a method to automatically construct datasets for ATE. We train a classifier on our automatically labelled datasets and evaluate it on the human annotated SemEval ABSA test sets. Compared to a strong rule-based baseline, we obtain a dramatically higher F-score and attain precision values above 80%. Our unsupervised method beats the supervised ABSA baseline from SemEval, while preserving high precision scores.