Semantification of Identifiers in Mathematics for Better Math Information Retrieval. Schubotz, M., Grigorev, A., Leich, M., Cohl, H. S., Meuschke, N., Gipp, B., Youssef, A. S., & Markl, V. In Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, of SIGIR '16, pages 135–144, New York, NY, USA, July, 2016. ACM. Venue Rating: CORE A*Paper doi abstract bibtex Mathematical formulae are essential in science, but face challenges of ambiguity, due to the use of a small number of identifiers to represent an immense number of concepts. Corresponding to word sense disambiguation in Natural Language Processing, we disambiguate mathematical identifiers. By regarding formulae and natural text as one monolithic information source, we are able to extract the semantics of identifiers in a process we term Mathematical Language Processing (MLP). As scientific communities tend to establish standard (identifier) notations, we use the document domain to infer the actual meaning of an identifier. Therefore, we adapt the software development concept of namespaces to mathematical notation. Thus, we learn namespace definitions by clustering the MLP results and mapping those clusters to subject classification schemata. In addition, this gives fundamental insights into the usage of mathematical notations in science, technology, engineering and mathematics. Our gold standard based evaluation shows that MLP extracts relevant identifier-definitions. Moreover, we discover that identifier namespaces improve the performance of automated identifier-definition extraction, and elevate it to a level that cannot be achieved within the document context alone.
@inproceedings{SchubotzGLC16,
address = {New York, NY, USA},
series = {{SIGIR} '16},
title = {Semantification of {Identifiers} in {Mathematics} for {Better} {Math} {Information} {Retrieval}},
isbn = {978-1-4503-4069-4},
shorttitle = {Semantification of {Identifiers} in {Mathematics} for {MIR}},
url = {https://www.gipp.com/wp-content/papercite-data/pdf/schubotz16.pdf},
doi = {10.1145/2911451.2911503},
abstract = {Mathematical formulae are essential in science, but face challenges of ambiguity, due to the use of a small number of identifiers to represent an immense number of concepts. Corresponding to word sense disambiguation in Natural Language Processing, we disambiguate mathematical identifiers. By regarding formulae and natural text as one monolithic information source, we are able to extract the semantics of identifiers in a process we term Mathematical Language Processing (MLP). As scientific communities tend to establish standard (identifier) notations, we use the document domain to infer the actual meaning of an identifier. Therefore, we adapt the software development concept of namespaces to mathematical notation. Thus, we learn namespace definitions by clustering the MLP results and mapping those clusters to subject classification schemata. In addition, this gives fundamental insights into the usage of mathematical notations in science, technology, engineering and mathematics. Our gold standard based evaluation shows that MLP extracts relevant identifier-definitions. Moreover, we discover that identifier namespaces improve the performance of automated identifier-definition extraction, and elevate it to a level that cannot be achieved within the document context alone.},
booktitle = {Proceedings of the 39th {International} {ACM} {SIGIR} {Conference} on {Research} and {Development} in {Information} {Retrieval}},
publisher = {ACM},
author = {Schubotz, Moritz and Grigorev, Alexey and Leich, Marcus and Cohl, Howard S. and Meuschke, Norman and Gipp, Bela and Youssef, Abdou S. and Markl, Volker},
month = jul,
year = {2016},
note = {Venue Rating: CORE A*},
keywords = {Math Information Retrieval},
pages = {135--144},
}
Downloads: 0
{"_id":"iAkGuZxn2qiYctrTn","bibbaseid":"schubotz-grigorev-leich-cohl-meuschke-gipp-youssef-markl-semantificationofidentifiersinmathematicsforbettermathinformationretrieval-2016","authorIDs":["3aamy24wTzcQoTPGY","7Crs4B84W7BbduMmq","97o4RCsEFAoSxEQqt","9dzP7gNRTLKvc9aPR","GYqCNzAZv2xc9nhmD","KLLNwF6yrTvRfDhAP","LKQ5pS2Y8Pc7FTkr7","TuCkHmKovwKzF3y8Z","ZDet9tokdva7KFSEH","ZJvJiH6kd887XEnz3","gBWY7RvNrDhhspCGi","nLJ4c698vfAyWRWTr","pCb6WupcebiMmhw8Y","qNrPNpAwKg5fp598G","s7Z2R2uTWDHRHN2bE","tFwG3DWb6fYeXs3sL","yiM4TojQ7StGdi2iD"],"author_short":["Schubotz, M.","Grigorev, A.","Leich, M.","Cohl, H. S.","Meuschke, N.","Gipp, B.","Youssef, A. S.","Markl, V."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"New York, NY, USA","series":"SIGIR '16","title":"Semantification of Identifiers in Mathematics for Better Math Information Retrieval","isbn":"978-1-4503-4069-4","shorttitle":"Semantification of Identifiers in Mathematics for MIR","url":"https://www.gipp.com/wp-content/papercite-data/pdf/schubotz16.pdf","doi":"10.1145/2911451.2911503","abstract":"Mathematical formulae are essential in science, but face challenges of ambiguity, due to the use of a small number of identifiers to represent an immense number of concepts. Corresponding to word sense disambiguation in Natural Language Processing, we disambiguate mathematical identifiers. By regarding formulae and natural text as one monolithic information source, we are able to extract the semantics of identifiers in a process we term Mathematical Language Processing (MLP). As scientific communities tend to establish standard (identifier) notations, we use the document domain to infer the actual meaning of an identifier. Therefore, we adapt the software development concept of namespaces to mathematical notation. Thus, we learn namespace definitions by clustering the MLP results and mapping those clusters to subject classification schemata. In addition, this gives fundamental insights into the usage of mathematical notations in science, technology, engineering and mathematics. Our gold standard based evaluation shows that MLP extracts relevant identifier-definitions. Moreover, we discover that identifier namespaces improve the performance of automated identifier-definition extraction, and elevate it to a level that cannot be achieved within the document context alone.","booktitle":"Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval","publisher":"ACM","author":[{"propositions":[],"lastnames":["Schubotz"],"firstnames":["Moritz"],"suffixes":[]},{"propositions":[],"lastnames":["Grigorev"],"firstnames":["Alexey"],"suffixes":[]},{"propositions":[],"lastnames":["Leich"],"firstnames":["Marcus"],"suffixes":[]},{"propositions":[],"lastnames":["Cohl"],"firstnames":["Howard","S."],"suffixes":[]},{"propositions":[],"lastnames":["Meuschke"],"firstnames":["Norman"],"suffixes":[]},{"propositions":[],"lastnames":["Gipp"],"firstnames":["Bela"],"suffixes":[]},{"propositions":[],"lastnames":["Youssef"],"firstnames":["Abdou","S."],"suffixes":[]},{"propositions":[],"lastnames":["Markl"],"firstnames":["Volker"],"suffixes":[]}],"month":"July","year":"2016","note":"Venue Rating: CORE A*","keywords":"Math Information Retrieval","pages":"135–144","bibtex":"@inproceedings{SchubotzGLC16,\n\taddress = {New York, NY, USA},\n\tseries = {{SIGIR} '16},\n\ttitle = {Semantification of {Identifiers} in {Mathematics} for {Better} {Math} {Information} {Retrieval}},\n\tisbn = {978-1-4503-4069-4},\n\tshorttitle = {Semantification of {Identifiers} in {Mathematics} for {MIR}},\n\turl = {https://www.gipp.com/wp-content/papercite-data/pdf/schubotz16.pdf},\n\tdoi = {10.1145/2911451.2911503},\n\tabstract = {Mathematical formulae are essential in science, but face challenges of ambiguity, due to the use of a small number of identifiers to represent an immense number of concepts. Corresponding to word sense disambiguation in Natural Language Processing, we disambiguate mathematical identifiers. By regarding formulae and natural text as one monolithic information source, we are able to extract the semantics of identifiers in a process we term Mathematical Language Processing (MLP). As scientific communities tend to establish standard (identifier) notations, we use the document domain to infer the actual meaning of an identifier. Therefore, we adapt the software development concept of namespaces to mathematical notation. Thus, we learn namespace definitions by clustering the MLP results and mapping those clusters to subject classification schemata. In addition, this gives fundamental insights into the usage of mathematical notations in science, technology, engineering and mathematics. Our gold standard based evaluation shows that MLP extracts relevant identifier-definitions. Moreover, we discover that identifier namespaces improve the performance of automated identifier-definition extraction, and elevate it to a level that cannot be achieved within the document context alone.},\n\tbooktitle = {Proceedings of the 39th {International} {ACM} {SIGIR} {Conference} on {Research} and {Development} in {Information} {Retrieval}},\n\tpublisher = {ACM},\n\tauthor = {Schubotz, Moritz and Grigorev, Alexey and Leich, Marcus and Cohl, Howard S. and Meuschke, Norman and Gipp, Bela and Youssef, Abdou S. and Markl, Volker},\n\tmonth = jul,\n\tyear = {2016},\n\tnote = {Venue Rating: CORE A*},\n\tkeywords = {Math Information Retrieval},\n\tpages = {135--144},\n}\n\n","author_short":["Schubotz, M.","Grigorev, A.","Leich, M.","Cohl, H. S.","Meuschke, N.","Gipp, B.","Youssef, A. S.","Markl, V."],"key":"SchubotzGLC16","id":"SchubotzGLC16","bibbaseid":"schubotz-grigorev-leich-cohl-meuschke-gipp-youssef-markl-semantificationofidentifiersinmathematicsforbettermathinformationretrieval-2016","role":"author","urls":{"Paper":"https://www.gipp.com/wp-content/papercite-data/pdf/schubotz16.pdf"},"keyword":["Math Information Retrieval"],"metadata":{"authorlinks":{"meuschke, n":"https://bibbase.org/show?bib=https%3A%2F%2Fapi.zotero.org%2Fgroups%2F2532143%2Fitems%3Fkey%3DDOjJ33bOgISaFjBIBr7jCV5S%26format%3Dbibtex%26limit%3D100"}},"downloads":0},"bibtype":"inproceedings","biburl":"https://api.zotero.org/groups/2532143/items?key=DOjJ33bOgISaFjBIBr7jCV5S&format=bibtex&limit=100","creationDate":"2020-04-15T13:02:33.680Z","downloads":0,"keywords":["math information retrieval"],"search_terms":["semantification","identifiers","mathematics","better","math","information","retrieval","schubotz","grigorev","leich","cohl","meuschke","gipp","youssef","markl"],"title":"Semantification of Identifiers in Mathematics for Better Math Information Retrieval","year":2016,"dataSources":["aEHCfX6B2taJt8dfa","9qTaLWxMN5hLpMP8m","xteq4cdC6ATE2G6Fg","JNgeyAG2vQ8k88oYh","FPjHiAkAja6XvmScK","QGwcHf7xnb5mCCQi7","RTGAqwGfLTSqYQMsS","Y7kZGjoN5Erk3Lo2J","yM7MefT3mRkY9m7i4","jnWJCpbQCoWvxj9kz","F32umBkhFrpeJbp7A","BWzEyLkMvdMGpHpr6","hBAe6Z5DsNbrQtje2","e3AdWzdxYmb85Fn5D","MtqPmSRuq4X8FJqNT","YCwvFifyPbazBYMQD","6oZMeYhGKA2Mp8xhF","gYMS6DBXsNosXKcRC","bQwdfx3o8Q3vnsqfH","SzFkcrpurPzNHEyqX","6KJgnNtYZiwwFkcGq","dHLtmS5G7GmooD755","EvZZTzAZvA3EsuMjm"]}