EARA: Improving Biomedical Semantic Textual Similarity with Entity-Aligned Attention and Retrieval Augmentation

Ying Xiong, Xin Yang, Linjing Liu, Ka-Chun Wong, Qingcai Chen, Yang Xiang, Buzhou Tang

Submission Type: Regular Long Paper

Submission Track: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.

Submission Track 2: Machine Learning for NLP

Keywords: Biomedical semantic textual similarity, entity-aligned regularization, retrival augmentation

Abstract: Measuring Semantic Textual Similarity (STS) is a fundamental task in biomedical text processing, which aims at quantifying the similarity between two input biomedical sentences. Unfortunately, the STS datasets in the biomedical domain are relatively smaller but more complex in semantics than common domain, often leading to overfitting issues and insufficient text representation even based on Pre-trained Language Models (PLMs) due to too many biomedical entities. In this paper, we propose EARA, an entity-aligned, attention-based and retrieval-augmented PLMs. Our proposed EARA first aligns the same type of fine-grained entity information in each sentence pair with an entity alignment matrix. Then, EARA regularizes the attention mechanism with an entity alignment matrix with an auxiliary loss. Finally, we add a retrieval module that retrieves similar instances to expand the scope of entity pairs and improve the model's generalization. The comprehensive experiments reflect that EARA can achieve state-of-the-art performance on both in-domain and out-of-domain datasets. Source code is available \footnote{https://github.com/xy-always/EARA}.

Submission Number: 1381