Unsupervised Neural Aspect Search with Related Terms Extraction

TL;DR

This paper introduces an unsupervised neural network with a convolutional multi-attention mechanism for extracting aspect-term pairs in natural language processing, improving multi-aspect extraction accuracy without labeled data.

Contribution

It proposes a novel unsupervised neural model with a special loss function for joint aspect and term extraction, especially in multi-aspect scenarios.

Findings

Increased precision in aspect-term pair extraction.

Improved aspect prediction accuracy.

Effective on real-world datasets.

Abstract

The tasks of aspect identification and term extraction remain challenging in natural language processing. While supervised methods achieve high scores, it is hard to use them in real-world applications due to the lack of labelled datasets. Unsupervised approaches outperform these methods on several tasks, but it is still a challenge to extract both an aspect and a corresponding term, particularly in the multi-aspect setting. In this work, we present a novel unsupervised neural network with convolutional multi-attention mechanism, that allows extracting pairs (aspect, term) simultaneously, and demonstrate the effectiveness on the real-world dataset. We apply a special loss aimed to improve the quality of multi-aspect extraction. The experimental study demonstrates, what with this loss we increase the precision not only on this joint setting but also on aspect prediction only.