Is searching full text more effective than searching abstracts? | BMC Bioinformatics | Full Text

Is searching full text more effective than searching abstracts? | BMC Bioinformatics | Full Text

With the growing availability of full-text articles online, scientists and other consumers of the life sciences literature now have the ability to go beyond searching bibliographic records (title, abstract, metadata) to directly access full-text content. Motivated by this emerging trend, I posed the following question: is searching full text more effective than searching abstracts? This question is answered by comparing text retrieval algorithms on MEDLINE® abstracts, full-text articles, and spans (paragraphs) within full-text articles using data from the TREC 2007 genomics track evaluation. Two retrieval models are examined: bm25 and the ranking algorithm implemented in the open-source Lucene search engine. Experiments show that treating an entire article as an indexing unit does not consistently yield higher effectiveness compared to abstract-only search. However, retrieval based on spans, or paragraphs-sized segments of full-text articles, consistently outperforms abstract-only sear

1 mentions: @lintool
Date: 2020/03/24 15:51

Referring Tweets

@lintool Relevant to recent efforts on searching the scientific literature - as it turns out, I worked on exactly this problem 10+ years ago: "Is searching full text more effective than searching abstracts?" t.co/JKHFWN8zGp

Related Entries

Read more [2002.01447] A Prototype of Serverless Lucenecontact arXivarXiv Twitter
0 users, 1 mentions 2020/02/05 15:51
Read more Cooking data: BigQuery ML vs the online dating spam - YouTube
0 users, 9 mentions 2020/02/11 03:50
Read more [DL輪読会]Set Transformer: A Framework for Attention-based Permutation-I…
0 users, 3 mentions 2020/02/25 12:51
Read more Online Workshop on Covid19@ELLIS on April 1st | European Lab for Learning & Intelligent Systems
0 users, 5 mentions 2020/03/27 17:20
Read more COVID-19 Open Research Datasetsearch icon
0 users, 1 mentions 2020/03/28 18:52