Hyperbolic Disentangled Representation for Fine-Grained Aspect Extraction

TL;DR

This paper introduces HDAE, a hyperbolic disentangled model that improves fine-grained aspect extraction from reviews by capturing hierarchical word relations and distinct seed word semantics, outperforming previous methods.

Contribution

HDAE is the first weakly supervised approach to utilize hyperbolic space for modeling hierarchical and disentangled seed word representations in aspect extraction.

Findings

HDAE achieves 18.2% and 24.1% F1 improvements on review datasets.

Visualization shows HDAE better leverages seed words.

Ablation studies confirm the effectiveness of HDAE components.

Abstract

Automatic identification of salient aspects from user reviews is especially useful for opinion analysis. There has been significant progress in utilizing weakly supervised approaches, which require only a small set of seed words for training aspect classifiers. However, there is always room for improvement. First, no weakly supervised approaches fully utilize latent hierarchies between words. Second, each seed words representation should have different latent semantics and be distinct when it represents a different aspect. In this paper, we propose HDAE, a hyperbolic disentangled aspect extractor in which a hyperbolic aspect classifier captures words latent hierarchies, and aspect-disentangled representation models the distinct latent semantics of each seed word. Compared to previous baselines, HDAE achieves average F1 performance gains of 18.2% and 24.1% on Amazon product review and restaurant review datasets, respectively. In addition, the em-bedding visualization experience demonstrates that HDAE is a more effective approach to leveraging seed words. An ablation study and a case study further attest to the effectiveness of the proposed components