ABSTRACT
Medical Frequently Asked Question (FAQ) retrieval aims to find the most relevant question-answer pairs for a given user query, which is of great significance for enhancing people medical health awareness and knowledge. However, due to medical data privacy and labor-intensive labeling, there is a lack of large-scale question-matching training datasets. Previous methods directly use the collected question-answer pairs on search engines to train retrieval models, which achieved poor performance. Inspired by recent advances in contrastive learning, we propose a novel contrastive curriculum learning framework for modeling user medical queries. First, we design different data augmentation methods to generate positive samples and different types of negative samples. Second, we propose a curriculum learning strategy that associates difficulty levels with negative samples. Through a contrastive learning process from easy to hard, our method achieves excellent results on two medical datasets. © 2022 IEEE.
ABSTRACT
Medical Frequently Asked Question (FAQ) retrieval aims to find the most relevant question-answer pairs for a given user query, which is of great significance for enhancing people medical health awareness and knowledge. However, due to medical data privacy and labor-intensive labeling, there is a lack of large-scale question-matching training datasets. Previous methods directly use the collected question-answer pairs on search engines to train retrieval models, which achieved poor performance. Inspired by recent advances in contrastive learning, we propose a novel contrastive curriculum learning framework for modeling user medical queries. First, we design different data augmentation methods to generate positive samples and different types of negative samples. Second, we propose a curriculum learning strategy that associates difficulty levels with negative samples. Through a contrastive learning process from easy to hard, our method achieves excellent results on two medical datasets. © 2022 IEEE.
ABSTRACT
Frequently Asked Question (F AQ) retrieval is a valuable task which aims to find the most relevant question-answer pair from a FAQ dataset given a user query. Currently, most works implement F AQ retrieval considering the similarity between the query and the question as well as the relevance between the query and the answer. However, the query-answer relevance is difficult to model effectively due to the heterogeneity of query-answer pairs in terms of syntax and semantics. To alleviate this issue and improve retrieval performance, we propose a novel approach to consider answer information into F AQ retrieval by question generation, which provides high-quality synthetic positive training examples for dense retriever. Experiment results indicate that our method outperforms term-based BM25 and pretrained dense retriever significantly on two recently published COVID-19 F AQ datasets. © 2021 IEEE.