Mining MEDLINE: abstracts, sentences, or phrases?

by: J Ding, D Berleant, D Nettleton, E Wurtele

Pac Symp Biocomput (2002), pp. 326-337.

View FullText article

Pubmed, Hubmed

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

yas, zlu, bundschu, T_lab (group), generif_paper (group), satre, ianturton

Find related articles with these CiteULike tags

annotation, bionlp, corpus, informationextraction, information-extraction, ppi, pubmed, ref-corpus, ref-transloc, textmining, text-mining

Abstract

A growing body of works address automated mining of biochemical knowledge from digital repositories of scientific literature, such as MEDLINE. Some of these works use abstracts as the unit of text from which to extract facts. Others use sentences for this purpose, while still others use phrases. Here we compare abstracts, sentences, and phrases in MEDLINE using the standard information retrieval performance measures of recall, precision, and effectiveness, for the task of mining interactions among biochemical terms based on term co-occurrence. Results show statistically significant differences that can impact the choice of text unit.

@article{citeulike:478761, abstract = {A growing body of works address automated mining of biochemical knowledge from digital repositories of scientific literature, such as MEDLINE. Some of these works use abstracts as the unit of text from which to extract facts. Others use sentences for this purpose, while still others use phrases. Here we compare abstracts, sentences, and phrases in MEDLINE using the standard information retrieval performance measures of recall, precision, and effectiveness, for the task of mining interactions among biochemical terms based on term co-occurrence. Results show statistically significant differences that can impact the choice of text unit.}, address = {Department of Electrical and Computer Engineering, Iowa State University, Ames, Iowa 50011, USA.}, author = {Ding, J. and Berleant, D. and Nettleton, D. and Wurtele, E. }, citeulike-article-id = {478761}, journal = {Pac Symp Biocomput}, keywords = {pubmed, text-mining}, pages = {326--337}, posted-at = {2008-07-24 17:02:51}, priority = {2}, title = {Mining MEDLINE: abstracts, sentences, or phrases?}, url = {http://view.ncbi.nlm.nih.gov/pubmed/11928487}, year = {2002} }

RIS record

TY - JOUR ID - citeulike:478761 L3 - citeulike-article-id:478761 TI - Mining MEDLINE: abstracts, sentences, or phrases? JF - Pac Symp Biocomput SP - 326 EP - 337 AD - Department of Electrical and Computer Engineering, Iowa State University, Ames, Iowa 50011, USA. N2 - A growing body of works address automated mining of biochemical knowledge from digital repositories of scientific literature, such as MEDLINE. Some of these works use abstracts as the unit of text from which to extract facts. Others use sentences for this purpose, while still others use phrases. Here we compare abstracts, sentences, and phrases in MEDLINE using the standard information retrieval performance measures of recall, precision, and effectiveness, for the task of mining interactions among biochemical terms based on term co-occurrence. Results show statistically significant differences that can impact the choice of text unit. KW - pubmed KW - text-mining AU - Ding, J AU - Berleant, D AU - Nettleton, D AU - Wurtele, E PY - 2002/// UR - http://view.ncbi.nlm.nih.gov/pubmed/11928487 ER -

RIS BibTeX