Why Machines Cannot Learn Mathematics, Yet. Greiner-Petter, A., Ruas, T., Schubotz, M., Aizawa, A., Grosky, W., & Gipp, B. In arXiv:1905.08359 [cs], May, 2019.
Paper abstract bibtex 2 downloads Nowadays, Machine Learning (ML) is seen as the universal solution to improve the effectiveness of information retrieval (IR) methods. However, while mathematics is a precise and accurate science, it is usually expressed by less accurate and imprecise descriptions, contributing to the relative dearth of machine learning applications for IR in this domain. Generally, mathematical documents communicate their knowledge with an ambiguous, context-dependent, and non-formal language. Given recent advances in ML, it seems canonical to apply ML techniques to represent and retrieve mathematics semantically. In this work, we apply popular text embedding techniques to the arXiv collection of STEM documents and explore how these are unable to properly understand mathematics from that corpus. In addition, we also investigate the missing aspects that would allow mathematics to be learned by computers.
@inproceedings{GreinerPetterRSA19a,
title = {Why {Machines} {Cannot} {Learn} {Mathematics}, {Yet}},
url = {http://ceur-ws.org/Vol-2414/paper14.pdf},
abstract = {Nowadays, Machine Learning (ML) is seen as the universal solution to improve the effectiveness of information retrieval (IR) methods. However, while mathematics is a precise and accurate science, it is usually expressed by less accurate and imprecise descriptions, contributing to the relative dearth of machine learning applications for IR in this domain. Generally, mathematical documents communicate their knowledge with an ambiguous, context-dependent, and non-formal language. Given recent advances in ML, it seems canonical to apply ML techniques to represent and retrieve mathematics semantically. In this work, we apply popular text embedding techniques to the arXiv collection of STEM documents and explore how these are unable to properly understand mathematics from that corpus. In addition, we also investigate the missing aspects that would allow mathematics to be learned by computers.},
urldate = {2020-12-18},
booktitle = {{arXiv}:1905.08359 [cs]},
author = {Greiner-Petter, André and Ruas, Terry and Schubotz, Moritz and Aizawa, Akiko and Grosky, William and Gipp, Bela},
month = may,
year = {2019},
keywords = {!tr\_author, Computer Science - Artificial Intelligence, Computer Science - Digital Libraries, Computer Science - Information Retrieval, machine\_learning, math, nlp, ⛔ No DOI found},
}
Downloads: 2
{"_id":"ztWM5aKELFc4AfYv4","bibbaseid":"greinerpetter-ruas-schubotz-aizawa-grosky-gipp-whymachinescannotlearnmathematicsyet-2019","authorIDs":["Gucpc4okfBdFDSePs"],"author_short":["Greiner-Petter, A.","Ruas, T.","Schubotz, M.","Aizawa, A.","Grosky, W.","Gipp, B."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Why Machines Cannot Learn Mathematics, Yet","url":"http://ceur-ws.org/Vol-2414/paper14.pdf","abstract":"Nowadays, Machine Learning (ML) is seen as the universal solution to improve the effectiveness of information retrieval (IR) methods. However, while mathematics is a precise and accurate science, it is usually expressed by less accurate and imprecise descriptions, contributing to the relative dearth of machine learning applications for IR in this domain. Generally, mathematical documents communicate their knowledge with an ambiguous, context-dependent, and non-formal language. Given recent advances in ML, it seems canonical to apply ML techniques to represent and retrieve mathematics semantically. In this work, we apply popular text embedding techniques to the arXiv collection of STEM documents and explore how these are unable to properly understand mathematics from that corpus. In addition, we also investigate the missing aspects that would allow mathematics to be learned by computers.","urldate":"2020-12-18","booktitle":"arXiv:1905.08359 [cs]","author":[{"propositions":[],"lastnames":["Greiner-Petter"],"firstnames":["André"],"suffixes":[]},{"propositions":[],"lastnames":["Ruas"],"firstnames":["Terry"],"suffixes":[]},{"propositions":[],"lastnames":["Schubotz"],"firstnames":["Moritz"],"suffixes":[]},{"propositions":[],"lastnames":["Aizawa"],"firstnames":["Akiko"],"suffixes":[]},{"propositions":[],"lastnames":["Grosky"],"firstnames":["William"],"suffixes":[]},{"propositions":[],"lastnames":["Gipp"],"firstnames":["Bela"],"suffixes":[]}],"month":"May","year":"2019","keywords":"!tr_author, Computer Science - Artificial Intelligence, Computer Science - Digital Libraries, Computer Science - Information Retrieval, machine_learning, math, nlp, ⛔ No DOI found","bibtex":"@inproceedings{GreinerPetterRSA19a,\n\ttitle = {Why {Machines} {Cannot} {Learn} {Mathematics}, {Yet}},\n\turl = {http://ceur-ws.org/Vol-2414/paper14.pdf},\n\tabstract = {Nowadays, Machine Learning (ML) is seen as the universal solution to improve the effectiveness of information retrieval (IR) methods. However, while mathematics is a precise and accurate science, it is usually expressed by less accurate and imprecise descriptions, contributing to the relative dearth of machine learning applications for IR in this domain. Generally, mathematical documents communicate their knowledge with an ambiguous, context-dependent, and non-formal language. Given recent advances in ML, it seems canonical to apply ML techniques to represent and retrieve mathematics semantically. In this work, we apply popular text embedding techniques to the arXiv collection of STEM documents and explore how these are unable to properly understand mathematics from that corpus. In addition, we also investigate the missing aspects that would allow mathematics to be learned by computers.},\n\turldate = {2020-12-18},\n\tbooktitle = {{arXiv}:1905.08359 [cs]},\n\tauthor = {Greiner-Petter, André and Ruas, Terry and Schubotz, Moritz and Aizawa, Akiko and Grosky, William and Gipp, Bela},\n\tmonth = may,\n\tyear = {2019},\n\tkeywords = {!tr\\_author, Computer Science - Artificial Intelligence, Computer Science - Digital Libraries, Computer Science - Information Retrieval, machine\\_learning, math, nlp, ⛔ No DOI found},\n}\n\n","author_short":["Greiner-Petter, A.","Ruas, T.","Schubotz, M.","Aizawa, A.","Grosky, W.","Gipp, B."],"key":"GreinerPetterRSA19a","id":"GreinerPetterRSA19a","bibbaseid":"greinerpetter-ruas-schubotz-aizawa-grosky-gipp-whymachinescannotlearnmathematicsyet-2019","role":"author","urls":{"Paper":"http://ceur-ws.org/Vol-2414/paper14.pdf"},"keyword":["!tr_author","Computer Science - Artificial Intelligence","Computer Science - Digital Libraries","Computer Science - Information Retrieval","machine_learning","math","nlp","⛔ No DOI found"],"metadata":{"authorlinks":{"ruas, t":"https://terryruas.com/pub/"}},"downloads":2},"bibtype":"inproceedings","biburl":"https://api.zotero.org/groups/2503580/items?key=9bMVo5bWhsSJ7a6YWgBxjXpk&format=bibtex&limit=100","creationDate":"2020-04-15T13:02:33.938Z","downloads":2,"keywords":["!tr_author","computer science - artificial intelligence","computer science - digital libraries","computer science - information retrieval","machine_learning","math","nlp","⛔ no doi found"],"search_terms":["machines","learn","mathematics","greiner-petter","ruas","schubotz","aizawa","grosky","gipp"],"title":"Why Machines Cannot Learn Mathematics, Yet","year":2019,"dataSources":["Zp98Nuv7ftsXLefzT","x2wNFgXC2PE23H45p","3wTLgXcXueP5mYbfu","cZ8X4Ke5so9b7csrB","wZtCXbB8M6GYSQHMx","F3AfGZZbixwqNK4mj","XJBi8b8xDjDoWPzcZ","kHqqD8pzLteJJWS2X","QGwcHf7xnb5mCCQi7","hG7rv86o2PDG2z44d","aJH3D6QaHCDgg2JGg"]}