Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs

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.

References in corpus (7)

• Decoupled Weight Decay Regularization
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Unsupervised Domain Adaptation by Backpropagation
• Traversing Knowledge Graphs in Vector Space
• NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
• Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning
• Predicting ConceptNet Path Quality Using Crowdsourced Assessments of Naturalness

Cited by in corpus (2)

• A Systematic Review of Aspect-based Sentiment Analysis: Domains, Methods, and Trends
• Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer