A Knowledge-Driven Approach to Classifying Object and Attribute Coreferences in Opinion Mining
This work addresses the challenge of improving opinion mining performance for applications like product reviews by reducing the need for time-consuming handcrafted knowledge bases, though it is incremental as it builds on existing coreference classification methods.
The paper tackled the problem of classifying object and attribute coreferences in opinion mining by proposing an approach that automatically mines domain-specific knowledge from unlabeled reviews and integrates it into a neural model, achieving effectiveness demonstrated on real-world datasets across five domains.
Classifying and resolving coreferences of objects (e.g., product names) and attributes (e.g., product aspects) in opinionated reviews is crucial for improving the opinion mining performance. However, the task is challenging as one often needs to consider domain-specific knowledge (e.g., iPad is a tablet and has aspect resolution) to identify coreferences in opinionated reviews. Also, compiling a handcrafted and curated domain-specific knowledge base for each domain is very time consuming and arduous. This paper proposes an approach to automatically mine and leverage domain-specific knowledge for classifying objects and attribute coreferences. The approach extracts domain-specific knowledge from unlabeled review data and trains a knowledgeaware neural coreference classification model to leverage (useful) domain knowledge together with general commonsense knowledge for the task. Experimental evaluation on realworld datasets involving five domains (product types) shows the effectiveness of the approach.