Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction

TL;DR

This paper introduces an unsupervised embedding approach that combines word and dependency path representations to improve aspect term extraction, achieving state-of-the-art results using only embedding features.

Contribution

The novel unsupervised embedding method models dependency paths as sequences and integrates syntactic information into aspect term extraction.

Findings

Embedding features alone achieve state-of-the-art results.

Incorporating syntactic dependency paths improves extraction performance.

The method outperforms existing embedding approaches in aspect extraction.

Abstract

In this paper, we develop a novel approach to aspect term extraction based on unsupervised learning of distributed representations of words and dependency paths. The basic idea is to connect two words (w1 and w2) with the dependency path (r) between them in the embedding space. Specifically, our method optimizes the objective w1 + r = w2 in the low-dimensional space, where the multi-hop dependency paths are treated as a sequence of grammatical relations and modeled by a recurrent neural network. Then, we design the embedding features that consider linear context and dependency context information, for the conditional random field (CRF) based aspect term extraction. Experimental results on the SemEval datasets show that, (1) with only embedding features, we can achieve state-of-the-art results; (2) our embedding method which incorporates the syntactic information among words yields better performance than other representative ones in aspect term extraction.