Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs

TL;DR

This paper presents a novel method combining knowledge graphs with Transformer models to improve cross-domain aspect term extraction, achieving state-of-the-art results and enhancing model robustness across different domains.

Contribution

The paper introduces a new approach for constructing domain-specific knowledge graphs and integrating them into Transformers via query enrichment and attention manipulation.

Findings

Achieves state-of-the-art performance on cross-domain datasets.

Shows that external knowledge improves Transformer-based aspect extraction.

Demonstrates robustness of the method across multiple domains.

Abstract

The extraction of aspect terms is a critical step in fine-grained sentiment analysis of text. Existing approaches for this task have yielded impressive results when the training and testing data are from the same domain. However, these methods show a drastic decrease in performance when applied to cross-domain settings where the domain of the testing data differs from that of the training data. To address this lack of extensibility and robustness, we propose a novel approach for automatically constructing domain-specific knowledge graphs that contain information relevant to the identification of aspect terms. We introduce a methodology for injecting information from these knowledge graphs into Transformer models, including two alternative mechanisms for knowledge insertion: via query enrichment and via manipulation of attention patterns. We demonstrate state-of-the-art performance on benchmark datasets for cross-domain aspect term extraction using our approach and investigate how the amount of external knowledge available to the Transformer impacts model performance.