ABSTRACT
Searching, reading, and finding information from the massive medical text collections are challenging. A typical biomedical search engine is not feasible to navigate each article to find critical information or keyphrases. Moreover, few tools provide a visualization of the relevant phrases to the query. However, there is a need to extract the keyphrases from each document for indexing and efficient search. The transformer-based neural networks-BERT has been used for various natural language processing tasks. The built-in self-attention mechanism can capture the associations between words and phrases in a sentence. This research investigates whether the self-attentions can be utilized to extract keyphrases from a document in an unsupervised manner and identify relevancy between phrases to construct a query relevancy phrase graph to visualize the search corpus phrases on their relevancy and importance. The comparison with six baseline methods shows that the self-attention-based unsupervised keyphrase extraction works well on a medical literature dataset. This unsupervised keyphrase extraction model can also be applied to other text data. The query relevancy graph model is applied to the COVID-19 literature dataset and to demonstrate that the attention-based phrase graph can successfully identify the medical phrases relevant to the query terms. © 2021 Copyright held by the owner/author(s). Publication rights licensed to ACM.
ABSTRACT
Consumers from non-medical backgrounds often look for information regarding a specific medical information need; however, they are limited by their lack of medical knowledge and may not be able to find reputable resources. As a case study, we investigate reducing this knowledge barrier to allow consumers to achieve search effectiveness comparable to that of an expert, or a medical professional, for COVID-19 related questions. We introduce and evaluate a hybrid index model that allows a consumer to formulate queries using consumer language to find relevant answers to COVID-19 questions. Our aim is to reduce performance degradation between medical professional queries and those of a consumer. We use a universal sentence embedding model to project consumer queries into the same semantic space as professional queries. We then incorporate sentence embeddings into a search framework alongside an inverted index. Documents from this index are retrieved using a novel scoring function that considers sentence embeddings and BM25 scoring. We find that our framework alleviates the expertise disparity, which we validate using an additional set of crowdsourced-consumer-queries even in an unsupervised setting. We also propose an extension of our method, where the sentence encoder is optimised in a supervised setup. Our framework allows for a consumer to search using consumer queries to match the search performance with that of a professional.