Bridging the Gap: Incorporating a Semantic Similarity Measure for Effectively Mapping PubMed Queries to Documents
This work addresses the problem of improving information retrieval for biomedical researchers by providing a more effective way to find relevant documents in PubMed, though it is incremental as it builds on existing semantic analysis methods.
The paper tackles the problem of mapping PubMed queries to documents by addressing the limitation of traditional word-matching IR methods, which fail when queries and documents share few words. It introduces a semantic similarity measure using neural word embeddings, achieving a 12% improvement in mean average precision over BM25 on TREC Genomics data and up to 25% better ranking scores when combined with BM25 on PubMed search logs.
The main approach of traditional information retrieval (IR) is to examine how many words from a query appear in a document. A drawback of this approach, however, is that it may fail to detect relevant documents where no or only few words from a query are found. The semantic analysis methods such as LSA (latent semantic analysis) and LDA (latent Dirichlet allocation) have been proposed to address the issue, but their performance is not superior compared to common IR approaches. Here we present a query-document similarity measure motivated by the Word Mover's Distance. Unlike other similarity measures, the proposed method relies on neural word embeddings to compute the distance between words. This process helps identify related words when no direct matches are found between a query and a document. Our method is efficient and straightforward to implement. The experimental results on TREC Genomics data show that our approach outperforms the BM25 ranking function by an average of 12% in mean average precision. Furthermore, for a real-world dataset collected from the PubMed search logs, we combine the semantic measure with BM25 using a learning to rank method, which leads to improved ranking scores by up to 25%. This experiment demonstrates that the proposed approach and BM25 nicely complement each other and together produce superior performance.