A Fast Deep Learning Model for Textual Relevance in Biomedical Information Retrieval

Abstract

Publications in the life sciences are characterized by a large technical vocabulary, with many lexical and semantic variations for expressing the same concept. Towards addressing the problem of relevance in biomedical literature search, we introduce a deep learning model for the relevance of a document's text to a keyword style query. Limited by a relatively small amount of training data, the model uses pre-trained word embeddings. With these, the model first computes a variable-length Delta matrix between the query and document, representing a difference between the two texts, which is then passed through a deep convolution stage followed by a deep feed-forward network to compute a relevance score. This results in a fast model suitable for use in an online search engine. The model is robust and outperforms comparable state-of-the-art deep learning approaches.

To appear in proceeding of WWW 2018

References in corpus (8)

• Efficient Estimation of Word Representations in Vector Space
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• End-to-End Neural Ad-hoc Ranking with Kernel Pooling
• Text Matching as Image Recognition
• Do Deep Convolutional Nets Really Need to be Deep and Convolutional?
• Neural Models for Information Retrieval
• Query Expansion with Locally-Trained Word Embeddings

Cited by in corpus (3)

• Personalized neural language models for real-world query auto completion
• Biomedical Evidence Generation Engine
• DeepVar: An End-to-End Deep Learning Approach for Genomic Variant Recognition in Biomedical Literature