Summarizing Topical Contents from PubMed Documents Using a Thematic Analysis

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 805–810, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Summarizing topical contents from PubMed documents using a thematic analysis Sun Kim, Lana Yeganova and W. John Wilbur National Center for Biotechnology Information National Library of Medicine, National Institutes of Health Bethesda, MD 20894, USA {sun.kim,yeganova,wilbur}@ncbi.nlm.nih.gov Abstract Improving the search and browsing ex- perience in PubMed® is a key compo- nent in helping users detect information of interest. In particular, when explor- ing a novel field, it is important to pro- vide a comprehensive view for a specific subject. One solution for providing this panoramic picture is to find sub-topics from a set of documents. We propose a method that finds sub-topics that we refer to as themes and computes representative titles based on a set of documents in each theme. The method combines a thematic clustering algorithm and the Pool Adja- cent Violators algorithm to induce signifi- cant themes. Then, for each theme, a title is computed using PubMed document ti- tles and theme-dependent term scores. We tested our system on five disease sets from OMIM® and evaluated the results based on normalized point-wise mutual informa- tion and MeSH® terms. For both perfor- mance measures, the proposed approach outperformed LDA. The quality of theme titles were also evaluated by comparing them with manually created titles. 1 Introduction PubMed1, currently a collection of about 25 mil- lion bibliographic records, has grown exponen- tially in size. With the abundance and diversity of information in PubMed many queries retrieve thousands of documents making it difficult for users to browse the results and identify the infor- mation most relevant to their topic of interest. The query ‘cystic fibrosis’, for example, retrieves pa- pers that discuss different aspects of the disease, including its clinical features, treatment options, 1http://pubmed.gov diagnosis, etc. A possible solution to this problem is to automatically group the retrieved documents into meaningful thematic clusters or themes (these terms are used interchangeably). However, clus- tering alone does not solve the problem entirely, as a significant amount of human post-processing is required to infer the topic of the cluster. There exists a vast collection of probabilistic clustering methods. One common problem among most of them is that different results are obtained depending on the cluster initialization, suggesting that some clusters are unstable or weak. How- ever, there is no obvious way to effectively and efficiently evaluate the quality of clusters. In this paper, we combine EM-based thematic cluster- ing (Kim and Wilbur, 2012) with the Pool Adja- cent Violators (PAV) algorithm (Ayer et al., 1955; Wilbur et al., 2005). PAV is an isotonic regression algorithm which we use as a method for convert- ing a score into a probability. Here, we show how PAV can be applied to evaluate the quality of clus- ters. Another issue that motivated this research is that most existing algorithms produce clusters that are not self-descriptive. Presenting meaningful titles can significantly improve the user …

Content truncated to 500 words