%0 Book Section %1 turney2001mining %A Turney, Peter %B Machine Learning: ECML 2001 %D 2001 %E Raedt, Luc De %E Flach, Peter %I Springer Berlin / Heidelberg %K 10_year_award 2001 2011 Mining award ecml_pkdd_2011 pmi-ir synonyms toefl versus web %P 491-502 %T Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL %U http://dx.doi.org/10.1007/3-540-44795-4_42 %V 2167 %X This paper presents a simple unsupervised learning algorithm for recognizing synonyms, based on statistical data acquired by querying a Web search engine. The algorithm, called PMI-IR, uses Pointwise Mutual Information (PMI) and Information Retrieval (IR) to measure the similarity of pairs of words. PMI-IR is empirically evaluated using 80 synonym test questions from the Test of English as a Foreign Language (TOEFL) and 50 synonym test questions from a collection of tests for students of English as a Second Language (ESL). On both tests, the algorithm obtains a score of 74%. PMI-IR is contrasted with Latent Semantic Analysis (LSA), which achieves a score of 64% on the same 80 TOEFL questions. The paper discusses potential applications of the new unsupervised learning algorithm and some implications of the results for LSA and LSI (Latent Semantic Indexing). %@ 978-3-540-42536-6

@incollection{turney2001mining, abstract = {This paper presents a simple unsupervised learning algorithm for recognizing synonyms, based on statistical data acquired by querying a Web search engine. The algorithm, called PMI-IR, uses Pointwise Mutual Information (PMI) and Information Retrieval (IR) to measure the similarity of pairs of words. PMI-IR is empirically evaluated using 80 synonym test questions from the Test of English as a Foreign Language (TOEFL) and 50 synonym test questions from a collection of tests for students of English as a Second Language (ESL). On both tests, the algorithm obtains a score of 74%. PMI-IR is contrasted with Latent Semantic Analysis (LSA), which achieves a score of 64% on the same 80 TOEFL questions. The paper discusses potential applications of the new unsupervised learning algorithm and some implications of the results for LSA and LSI (Latent Semantic Indexing).}, added-at = {2011-09-03T12:02:05.000+0200}, affiliation = {National Research Council of Canada Institute for Information Technology M-50 Montreal Road Ottawa Ontario Canada K1A 0R6}, author = {Turney, Peter}, biburl = {https://www.bibsonomy.org/bibtex/262b5ae40c43d87930274e31020b42cac/ecml_pkdd_2011}, booktitle = {Machine Learning: ECML 2001}, editor = {Raedt, Luc De and Flach, Peter}, interhash = {8e5ac4302379bb3e66512a3696669bcb}, intrahash = {62b5ae40c43d87930274e31020b42cac}, isbn = {978-3-540-42536-6}, keyword = {Computer Science}, keywords = {10_year_award 2001 2011 Mining award ecml_pkdd_2011 pmi-ir synonyms toefl versus web}, note = {10.1007/3-540-44795-4_42}, pages = {491-502}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, timestamp = {2011-09-03T12:02:05.000+0200}, title = {Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL}, url = {http://dx.doi.org/10.1007/3-540-44795-4_42}, volume = 2167, year = 2001 }