Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents
This work addresses a domain-specific problem in natural language processing for applications like question answering and retrieval, offering an incremental improvement over existing methods.
The paper tackles text semantic matching by separating keywords and intents to handle different matching granularities, achieving stable performance improvements across three benchmarks when combined with pre-trained language models.
Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, directly perform text comparison by processing each word uniformly. However, a query sentence generally comprises content that calls for different levels of matching granularity. Specifically, keywords represent factual information such as action, entity, and event that should be strictly matched, while intents convey abstract concepts and ideas that can be paraphrased into various expressions. In this work, we propose a simple yet effective training strategy for text semantic matching in a divide-and-conquer manner by disentangling keywords from intents. Our approach can be easily combined with pre-trained language models (PLM) without influencing their inference efficiency, achieving stable performance improvements against a wide range of PLMs on three benchmarks.