PubMed related articles: a probabilistic topic-based model for content similarity

by: Jimmy Lin, John W Wilbur

BMC Bioinformatics, Vol. 8, No. 1. (2007)

View FullText article

DOI, Pubmed, Hubmed

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

yas, jyuh, dullhunk, msampson, Gaetan, barriot, A_Hoogendam

Find related articles with these CiteULike tags

articles, literature, no-tag, pubmed, related, similarity, text, text-mining, updating

Abstract

BACKGROUND:We present a probabilistic topic-based model for content similarity called pmra that underlies the related article search feature in PubMed. Whether or not a document is about a particular topic is computed from term frequencies, modeled as Poisson distributions. Unlike previous probabilistic retrieval models, we do not attempt to estimate relevance---but rather our focus is "relatedness", the probability that a user would want to examine a particular document given known interest in another. We also describe a novel technique for estimating parameters that does not require human relevance judgments; instead, the process is based on the existence of MeSH in MEDLINE.RESULTS:The pmra retrieval model was compared against bm25, a competitive probabilistic model that shares theoretical similarities. Experiments using the test collection from the TREC 2005 genomics track shows a small but statistically significant improvement of pmra over bm25 in terms of precision.CONCLUSIONS:Our experiments suggest that the pmra model provides an effective ranking algorithm for related article search.

@article{citeulike:1845865, abstract = {BACKGROUND:We present a probabilistic topic-based model for content similarity called pmra that underlies the related article search feature in PubMed. Whether or not a document is about a particular topic is computed from term frequencies, modeled as Poisson distributions. Unlike previous probabilistic retrieval models, we do not attempt to estimate relevance---but rather our focus is "relatedness", the probability that a user would want to examine a particular document given known interest in another. We also describe a novel technique for estimating parameters that does not require human relevance judgments; instead, the process is based on the existence of MeSH in MEDLINE.RESULTS:The pmra retrieval model was compared against bm25, a competitive probabilistic model that shares theoretical similarities. Experiments using the test collection from the TREC 2005 genomics track shows a small but statistically significant improvement of pmra over bm25 in terms of precision.CONCLUSIONS:Our experiments suggest that the pmra model provides an effective ranking algorithm for related article search.}, author = {Lin, Jimmy and Wilbur, John W. }, citeulike-article-id = {1845865}, doi = {10.1186/1471-2105-8-423}, journal = {BMC Bioinformatics}, keywords = {text-mining}, number = {1}, posted-at = {2008-05-14 10:04:32}, priority = {2}, title = {PubMed related articles: a probabilistic topic-based model for content similarity}, url = {http://dx.doi.org/10.1186/1471-2105-8-423}, volume = {8}, year = {2007} }

RIS record

TY - JOUR ID - citeulike:1845865 L3 - citeulike-article-id:1845865 TI - PubMed related articles: a probabilistic topic-based model for content similarity JF - BMC Bioinformatics VL - 8 IS - 1 N2 - BACKGROUND:We present a probabilistic topic-based model for content similarity called pmra that underlies the related article search feature in PubMed. Whether or not a document is about a particular topic is computed from term frequencies, modeled as Poisson distributions. Unlike previous probabilistic retrieval models, we do not attempt to estimate relevance---but rather our focus is "relatedness", the probability that a user would want to examine a particular document given known interest in another. We also describe a novel technique for estimating parameters that does not require human relevance judgments; instead, the process is based on the existence of MeSH in MEDLINE.RESULTS:The pmra retrieval model was compared against bm25, a competitive probabilistic model that shares theoretical similarities. Experiments using the test collection from the TREC 2005 genomics track shows a small but statistically significant improvement of pmra over bm25 in terms of precision.CONCLUSIONS:Our experiments suggest that the pmra model provides an effective ranking algorithm for related article search. KW - text-mining AU - Lin, Jimmy AU - Wilbur, John PY - 2007/// UR - http://dx.doi.org/10.1186/1471-2105-8-423 ER -

RIS BibTeX