A supervised term ranking model for diversity enhanced biomedical information retrieval

Abstract

BackgroundThe number of biomedical research articles have increased exponentially with the advancement of biomedicine in recent years. These articles have thus brought a great difficulty in obtaining the needed information of researchers. Information retrieval technologies seek to tackle the problem. However, information needs cannot be completely satisfied by directly introducing the existing information retrieval techniques. Therefore, biomedical information retrieval not only focuses on the relevance of search results, but also aims to promote the completeness of the results, which is referred as the diversity-oriented retrieval.ResultsWe address the diversity-oriented biomedical retrieval task using a supervised term ranking model. The model is learned through a supervised query expansion process for term refinement. Based on the model, the most relevant and diversified terms are selected to enrich the original query. The expanded query is then fed into a second retrieval to improve the relevance and diversity of search results. To this end, we propose three diversity-oriented optimization strategies in our model, including the diversified term labeling strategy, the biomedical resource-based term features and a diversity-oriented group sampling learning method. Experimental results on TREC Genomics collections demonstrate the effectiveness of the proposed model in improving the relevance and the diversity of search results.ConclusionsThe proposed three strategies jointly contribute to the improvement of biomedical retrieval performance. Our model yields more relevant and diversified results than the state-of-the-art baseline models. Moreover, our method provides a general framework for improving biomedical retrieval performance, and can be used as the basis for future work.

Contextual Query Expansion for Conducting Technology-Assisted Biomedical Reviews

“…The work presented in [10], experimentally evaluates expanding queries with synonyms derived from their MeSH terms and UMLS concepts, and concludes that these strategies are more effective than PubMed's standard Automatic Term Mapping or ATM [10] in terms of different retrieval metrics such a s precision and recall. The approach presented in [11] aims to use a supervised term ranking model to achieve diversity-oriented retrieval for biomedical information. Here, the objective is to search for a biomedical research question from different perspectives by retrieving studies that are related to the different aspects of a given query.…”

A Query Expansion Method Using Multinomial Naive Bayes

“…Xu et al [8] proposed a supervised query expansion model that could be applied to highly diverse biomedical datasets. The authors performed a term extraction for each query, proceeded to assign labels to each term, and then ranked them to know which were the most relevant.…”

An Algorithm of Query Expansion for Chinese EMR Retrieval by Improving Expansion Term Weights and Retrieval Scores

“…Park et al [18] select expansion terms and assign weights by syntactic features extracted from dependency parsing results of verbose queries. Xu et al [19] use supervised term ranking models and assigned weights based on learned term features. Summarizing the existing research, we can see that these methods ignore some unique characteristics of Chinese EMR retrieval, and the training datasets needed by supervised learning models are difficult to construct due to the cost of manual labeling.…”