{ "ok": true, "doi": "10.46243/jst.2018.v3.i06.pp59-67", "events": [ { "seq": 1, "kind": "register", "at": "2026-09-29 22:00:33", "by": "Administrator (admin)", "by_kind": "user", "note": "registered at Crossref; record read from api.crossref.org", "changes": [ { "path": "abstract.lang", "from": null, "to": "en" }, { "path": "abstract.value", "from": null, "to": "The continuous Skip-gram model, which was recently presented, is a quick and easy way to build high-quality distributed vector representations that capture a huge number of accurate syntactic and semantic word associations. We provide numerous enhancements in this study that improve the quality of the vectors as well as the training speed. We get a considerable speedup and learn more regular word representations by subsampling the frequent words. We also discuss negative sampling,which is a simple alternative to hierarchical softmax. The indifference to word order and inability to capture idiomatic phrases are two fundamental limitations of word representations. The meanings of \"Canada\" and \"Air,\" for example, cannot simply be merged to become \"Air Canada." }, { "path": "agents.0.name.family", "from": null, "to": "Rao" }, { "path": "agents.0.name.given", "from": null, "to": "Mr.D.Koteswara" }, { "path": "agents.0.role", "from": null, "to": "author" }, { "path": "agents.0.sequence", "from": null, "to": "first" }, { "path": "agents.1.name.family", "from": null, "to": "Kumar" }, { "path": "agents.1.name.given", "from": null, "to": "Mr.T.Rathna" }, { "path": "agents.1.role", "from": null, "to": "author" }, { "path": "agents.1.sequence", "from": null, "to": "additional" }, { "path": "agents.2.name.family", "from": null, "to": "Vineela" }, { "path": "agents.2.name.given", "from": null, "to": "Mrs.K." }, { "path": "agents.2.role", "from": null, "to": "author" }, { "path": "agents.2.sequence", "from": null, "to": "additional" }, { "path": "agents.3.name.family", "from": null, "to": "Jyothi" }, { "path": "agents.3.name.given", "from": null, "to": "Mrs.B.Rama" }, { "path": "agents.3.role", "from": null, "to": "author" }, { "path": "agents.3.sequence", "from": null, "to": "additional" }, { "path": "agents.4.name.org", "from": null, "to": "Longman Publishers" }, { "path": "agents.4.role", "from": null, "to": "publisher" }, { "path": "characters.0", "from": null, "to": "Language" }, { "path": "container.identifiers.0.medium", "from": null, "to": "electronic" }, { "path": "container.identifiers.0.type", "from": null, "to": "ISSN" }, { "path": "container.identifiers.0.value", "from": null, "to": "2456-5660" }, { "path": "container.issue", "from": null, "to": "06" }, { "path": "container.pages.first", "from": null, "to": "59" }, { "path": "container.pages.last", "from": null, "to": "67" }, { "path": "container.titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "container.titles.0.value", "from": null, "to": "Journal of Science & Technology" }, { "path": "container.type", "from": null, "to": "Journal" }, { "path": "container.volume", "from": null, "to": "03" }, { "path": "dates.date_type", "from": null, "to": "PublicationDate" }, { "path": "dates.online", "from": null, "to": "2018-11-21" }, { "path": "dates.published", "from": null, "to": "2018-11-21" }, { "path": "doi", "from": null, "to": "10.46243/jst.2018.v3.i06.pp59-67" }, { "path": "format", "from": null, "to": "smartscholars-doi-metadata/1.0" }, { "path": "identifiers.0.type", "from": null, "to": "DOI" }, { "path": "identifiers.0.value", "from": null, "to": "10.46243/jst.2018.v3.i06.pp59-67" }, { "path": "language", "from": null, "to": "en" }, { "path": "license.applies_to", "from": null, "to": "vor" }, { "path": "license.start", "from": null, "to": "2018-11-21" }, { "path": "license.url", "from": null, "to": "https://creativecommons.org/licenses/by/4.0/" }, { "path": "links.0.primary", "from": null, "to": true }, { "path": "links.0.return_type", "from": null, "to": "text/html" }, { "path": "links.0.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/view/161" }, { "path": "links.1.purpose", "from": null, "to": "text-mining" }, { "path": "links.1.return_type", "from": null, "to": "application/pdf" }, { "path": "links.1.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/161/140" }, { "path": "links.2.purpose", "from": null, "to": "text-mining" }, { "path": "links.2.return_type", "from": null, "to": "application/xml" }, { "path": "links.2.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/161/3446" }, { "path": "links.3.purpose", "from": null, "to": "similarity-checking" }, { "path": "links.3.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/view/161/140" }, { "path": "modes.0", "from": null, "to": "Visual" }, { "path": "record.issue_number", "from": null, "to": 1 }, { "path": "record.registered", "from": null, "to": "2026-09-07" }, { "path": "record.registrant", "from": null, "to": "Longman Publishers" }, { "path": "record.source", "from": null, "to": "crossref-api" }, { "path": "record.source_agency", "from": null, "to": "Crossref (member 25296)" }, { "path": "record.updated", "from": null, "to": "2026-09-20" }, { "path": "references.0.doi", "from": null, "to": "10.1145/2635868.2635883" }, { "path": "references.0.key", "from": null, "to": "ref1" }, { "path": "references.0.unstructured", "from": null, "to": "MiltiadisAllamanis, Earl T. Barr, Christian Bird, and Charles Sutton. 2014. Learning Natural Coding Conventions. In Proceedings of the 22Nd ACM SIGSOFT International Symposium on Foundations of Software Engineering (FSE 2014). ACM, New York, NY, USA, 281ś293" }, { "path": "references.1.doi", "from": null, "to": "10.1145/2635868.2635883" }, { "path": "references.1.key", "from": null, "to": "ref2" }, { "path": "references.1.unstructured", "from": null, "to": "https://doi.org/10.1145/2635868.2635883 MiltiadisAllamanis, Earl T. Barr, Christian Bird, and Charles Sutton. 2015a. Suggesting Accurate Method and Class Names. In Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering (ESEC/FSE 2015)" }, { "path": "references.10.key", "from": null, "to": "ref11" }, { "path": "references.10.unstructured", "from": null, "to": "2010. Neural conditional random fields. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. 177ś184. Jimmy Ba, VolodymyrMnih, and KorayKavukcuoglu. 2014. Multiple object recognition with visual attention" }, { "path": "references.11.key", "from": null, "to": "ref12" }, { "path": "references.11.unstructured", "from": null, "to": "arXiv preprint arXiv:1412.7755 (2014). DzmitryBahdanau, Kyunghyun Cho, and YoshuaBengio. 2014. Neural Machine Translation by Jointly Learning to Align and Translate. CoRR abs/1409.0473 (2014). http://arxiv.org/abs/1409.0473 DzmitryBahdanau, Jan Chorowski, DmitriySerdyuk, Philemon Brakel, and YoshuaBengio. 2016. End-to-end attentionbased large vocabulary speech recognition" }, { "path": "references.12.doi", "from": null, "to": "10.1109/icassp.2003.1199851" }, { "path": "references.12.key", "from": null, "to": "ref13" }, { "path": "references.12.unstructured", "from": null, "to": "In Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE, 4945ś4949. YoshuaBengio, RéjeanDucharme, Pascal Vincent, and Christian Janvin. 2003. A Neural Probabilistic Language Model. J. Mach. Learn. Res. 3 (March 2003), 1137ś1155" }, { "path": "references.13.key", "from": null, "to": "ref14" }, { "path": "references.13.unstructured", "from": null, "to": "http://dl.acm.org/citation.cfm?id=944919.944966 PavolBielik, VeselinRaychev, and Martin T. Vechev. 2016. PHOG: Probabilistic Model for Code. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016. 2933ś2942. http://jmlr.org/proceedings/papers/v48/bielik16.html Chris Callison-Burch, Miles Osborne, and Philipp Koehn. 2006. Re-evaluation the role of bleu in machine translation research" }, { "path": "references.14.key", "from": null, "to": "ref15" }, { "path": "references.14.unstructured", "from": null, "to": "In 11th Conference of the European Chapter of the Association for Computational Linguistics. Jan KChorowski, DzmitryBahdanau, DmitriySerdyuk, Kyunghyun Cho, and YoshuaBengio. 2015. Attention-based models for speech recognition. In Advances in Neural Information Processing Systems. 577ś585. Ronan Collobert and Jason Weston" }, { "path": "references.15.doi", "from": null, "to": "10.1145/1390156.1390177" }, { "path": "references.15.key", "from": null, "to": "ref16" }, { "path": "references.15.unstructured", "from": null, "to": "2008. A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. In Proceedings of the 25th International Conference on Machine Learning (ICML ’08). ACM, New York, NY, USA, 160ś167. https://doi.org/10.1145/1390156.1390177 Yaniv David, Nimrod Partush, and EranYahav. 2016. Statistical Similarity in Binaries. In PLDI’16: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation. Yaniv David, Nimrod Partush, and EranYahav" }, { "path": "references.16.doi", "from": null, "to": "10.1145/3062341.3062387" }, { "path": "references.16.key", "from": null, "to": "ref17" }, { "path": "references.16.unstructured", "from": null, "to": "2017. Similarity of Binaries through re-optimization. In PLDI’17: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation" }, { "path": "references.2.doi", "from": null, "to": "10.1145/2786805.2786849" }, { "path": "references.2.key", "from": null, "to": "ref3" }, { "path": "references.2.unstructured", "from": null, "to": "ACM, New York, NY, USA, 38ś49. https://doi.org/10.1145/2786805.2786849 MiltiadisAllamanis, Earl T Barr, PremkumarDevanbu, and Charles Sutton. 2017. A Survey of Machine Learning for Big Code and Naturalness. arXiv preprint arXiv:1709.06182 (2017)" }, { "path": "references.3.key", "from": null, "to": "ref4" }, { "path": "references.3.unstructured", "from": null, "to": "MiltiadisAllamanis, Marc Brockschmidt, and Mahmoud Khademi. 2018. Learning to Represent Programs with Graphs. In ICLR. MiltiadisAllamanis, HaoPeng, and Charles A. Sutton. 2016. A Convolutional Attention Network for Extreme Summarization of Source Code" }, { "path": "references.4.key", "from": null, "to": "ref5" }, { "path": "references.4.unstructured", "from": null, "to": "In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19- 24, 2016. 2091ś2100. http://jmlr.org/proceedings/papers/v48/allamanis16.html MiltiadisAllamanis and Charles Sutton" }, { "path": "references.5.doi", "from": null, "to": "10.1109/msr.2013.6624029" }, { "path": "references.5.key", "from": null, "to": "ref6" }, { "path": "references.5.unstructured", "from": null, "to": "2013. Mining Source Code Repositories at Massive Scale Using Language Modeling. In Proceedings of the 10th Working Conference on Mining Software Repositories (MSR ’13). IEEE Press, Piscataway, NJ, USA, 207ś216" }, { "path": "references.6.doi", "from": null, "to": "10.1145/2635868.2635901" }, { "path": "references.6.key", "from": null, "to": "ref7" }, { "path": "references.6.unstructured", "from": null, "to": "http://dl.acm.org/citation.cfm?id=2487085.2487127 MiltiadisAllamanis and Charles Sutton. 2014. Mining Idioms from Source Code. In Proceedings of the 22Nd ACM SIGSOFT International Symposium on Foundations of Software Engineering (FSE 2014). ACM, New York, NY, USA, 472ś483. https: //doi.org/10.1145/2635868.2635901 MiltiadisAllamanis, Daniel Tarlow, Andrew D. Gordon, and Yi Wei. 2015b. Bimodal Modelling of Source Code and Natural Language" }, { "path": "references.7.key", "from": null, "to": "ref8" }, { "path": "references.7.unstructured", "from": null, "to": "In Proceedings of the 32nd International Conference on International Conference on Machine Learning-Volume 37 (ICML’15). JMLR.org, 2123ś2132. http://dl.acm.org/citation.cfm?id=3045118.3045344 Uri Alon, MeitalZilberstein, Omer Levy, and EranYahav. 2018. A General Path-based Representation for Predicting Program Properties" }, { "path": "references.8.doi", "from": null, "to": "10.1145/3192366" }, { "path": "references.8.key", "from": null, "to": "ref9" }, { "path": "references.8.unstructured", "from": null, "to": "In Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2018). ACM, New York, NY, USA, 404ś419" }, { "path": "references.9.key", "from": null, "to": "ref10" }, { "path": "references.9.unstructured", "from": null, "to": "Matthew Amodio, SwaratChaudhuri, and Thomas W. Reps. 2017. Neural Attribute Machines for Program Generation. CoRR abs/1705.09231 (2017). arXiv:1705.09231 http://arxiv.org/abs/1705.09231 Thierry Artieres et al" }, { "path": "referent", "from": null, "to": "Creation" }, { "path": "structural_type", "from": null, "to": "Digital" }, { "path": "titles.0.lang", "from": null, "to": "en" }, { "path": "titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "titles.0.value", "from": null, "to": "DISTRIBUTED REPRESENTATIONS OF AWORD: A SURVEY" }, { "path": "type", "from": null, "to": "JournalArticle" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2018.v3.i06.pp59-67", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "DISTRIBUTED REPRESENTATIONS OF AWORD: A SURVEY", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2018.v3.i06.pp59-67" } ], "agents": [ { "role": "author", "name": { "given": "Mr.D.Koteswara", "family": "Rao" }, "sequence": "first" }, { "role": "author", "name": { "given": "Mr.T.Rathna", "family": "Kumar" }, "sequence": "additional" }, { "role": "author", "name": { "given": "Mrs.K.", "family": "Vineela" }, "sequence": "additional" }, { "role": "author", "name": { "given": "Mrs.B.Rama", "family": "Jyothi" }, "sequence": "additional" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2018-11-21", "date_type": "PublicationDate", "online": "2018-11-21" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "03", "issue": "06", "pages": { "first": "59", "last": "67" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/161", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/161/140", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/161/3446", "purpose": "text-mining", "return_type": "application/xml" }, { "url": "https://www.jst.org.in/index.php/pub/article/view/161/140", "purpose": "similarity-checking" } ], "abstract": { "value": "The continuous Skip-gram model, which was recently presented, is a quick and easy way to build high-quality distributed vector representations that capture a huge number of accurate syntactic and semantic word associations. We provide numerous enhancements in this study that improve the quality of the vectors as well as the training speed. We get a considerable speedup and learn more regular word representations by subsampling the frequent words. We also discuss negative sampling,which is a simple alternative to hierarchical softmax. The indifference to word order and inability to capture idiomatic phrases are two fundamental limitations of word representations. The meanings of \"Canada\" and \"Air,\" for example, cannot simply be merged to become \"Air Canada.", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2018-11-21", "applies_to": "vor" }, "references": [ { "key": "ref1", "doi": "10.1145/2635868.2635883", "unstructured": "MiltiadisAllamanis, Earl T. Barr, Christian Bird, and Charles Sutton. 2014. Learning Natural Coding Conventions. In Proceedings of the 22Nd ACM SIGSOFT International Symposium on Foundations of Software Engineering (FSE 2014). ACM, New York, NY, USA, 281ś293" }, { "key": "ref2", "doi": "10.1145/2635868.2635883", "unstructured": "https://doi.org/10.1145/2635868.2635883 MiltiadisAllamanis, Earl T. Barr, Christian Bird, and Charles Sutton. 2015a. Suggesting Accurate Method and Class Names. In Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering (ESEC/FSE 2015)" }, { "key": "ref3", "doi": "10.1145/2786805.2786849", "unstructured": "ACM, New York, NY, USA, 38ś49. https://doi.org/10.1145/2786805.2786849 MiltiadisAllamanis, Earl T Barr, PremkumarDevanbu, and Charles Sutton. 2017. A Survey of Machine Learning for Big Code and Naturalness. arXiv preprint arXiv:1709.06182 (2017)" }, { "key": "ref4", "unstructured": "MiltiadisAllamanis, Marc Brockschmidt, and Mahmoud Khademi. 2018. Learning to Represent Programs with Graphs. In ICLR. MiltiadisAllamanis, HaoPeng, and Charles A. Sutton. 2016. A Convolutional Attention Network for Extreme Summarization of Source Code" }, { "key": "ref5", "unstructured": "In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19- 24, 2016. 2091ś2100. http://jmlr.org/proceedings/papers/v48/allamanis16.html MiltiadisAllamanis and Charles Sutton" }, { "key": "ref6", "doi": "10.1109/msr.2013.6624029", "unstructured": "2013. Mining Source Code Repositories at Massive Scale Using Language Modeling. In Proceedings of the 10th Working Conference on Mining Software Repositories (MSR ’13). IEEE Press, Piscataway, NJ, USA, 207ś216" }, { "key": "ref7", "doi": "10.1145/2635868.2635901", "unstructured": "http://dl.acm.org/citation.cfm?id=2487085.2487127 MiltiadisAllamanis and Charles Sutton. 2014. Mining Idioms from Source Code. In Proceedings of the 22Nd ACM SIGSOFT International Symposium on Foundations of Software Engineering (FSE 2014). ACM, New York, NY, USA, 472ś483. https: //doi.org/10.1145/2635868.2635901 MiltiadisAllamanis, Daniel Tarlow, Andrew D. Gordon, and Yi Wei. 2015b. Bimodal Modelling of Source Code and Natural Language" }, { "key": "ref8", "unstructured": "In Proceedings of the 32nd International Conference on International Conference on Machine Learning-Volume 37 (ICML’15). JMLR.org, 2123ś2132. http://dl.acm.org/citation.cfm?id=3045118.3045344 Uri Alon, MeitalZilberstein, Omer Levy, and EranYahav. 2018. A General Path-based Representation for Predicting Program Properties" }, { "key": "ref9", "doi": "10.1145/3192366", "unstructured": "In Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2018). ACM, New York, NY, USA, 404ś419" }, { "key": "ref10", "unstructured": "Matthew Amodio, SwaratChaudhuri, and Thomas W. Reps. 2017. Neural Attribute Machines for Program Generation. CoRR abs/1705.09231 (2017). arXiv:1705.09231 http://arxiv.org/abs/1705.09231 Thierry Artieres et al" }, { "key": "ref11", "unstructured": "2010. Neural conditional random fields. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. 177ś184. Jimmy Ba, VolodymyrMnih, and KorayKavukcuoglu. 2014. Multiple object recognition with visual attention" }, { "key": "ref12", "unstructured": "arXiv preprint arXiv:1412.7755 (2014). DzmitryBahdanau, Kyunghyun Cho, and YoshuaBengio. 2014. Neural Machine Translation by Jointly Learning to Align and Translate. CoRR abs/1409.0473 (2014). http://arxiv.org/abs/1409.0473 DzmitryBahdanau, Jan Chorowski, DmitriySerdyuk, Philemon Brakel, and YoshuaBengio. 2016. End-to-end attentionbased large vocabulary speech recognition" }, { "key": "ref13", "doi": "10.1109/icassp.2003.1199851", "unstructured": "In Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE, 4945ś4949. YoshuaBengio, RéjeanDucharme, Pascal Vincent, and Christian Janvin. 2003. A Neural Probabilistic Language Model. J. Mach. Learn. Res. 3 (March 2003), 1137ś1155" }, { "key": "ref14", "unstructured": "http://dl.acm.org/citation.cfm?id=944919.944966 PavolBielik, VeselinRaychev, and Martin T. Vechev. 2016. PHOG: Probabilistic Model for Code. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016. 2933ś2942. http://jmlr.org/proceedings/papers/v48/bielik16.html Chris Callison-Burch, Miles Osborne, and Philipp Koehn. 2006. Re-evaluation the role of bleu in machine translation research" }, { "key": "ref15", "unstructured": "In 11th Conference of the European Chapter of the Association for Computational Linguistics. Jan KChorowski, DzmitryBahdanau, DmitriySerdyuk, Kyunghyun Cho, and YoshuaBengio. 2015. Attention-based models for speech recognition. In Advances in Neural Information Processing Systems. 577ś585. Ronan Collobert and Jason Weston" }, { "key": "ref16", "doi": "10.1145/1390156.1390177", "unstructured": "2008. A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. In Proceedings of the 25th International Conference on Machine Learning (ICML ’08). ACM, New York, NY, USA, 160ś167. https://doi.org/10.1145/1390156.1390177 Yaniv David, Nimrod Partush, and EranYahav. 2016. Statistical Similarity in Binaries. In PLDI’16: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation. Yaniv David, Nimrod Partush, and EranYahav" }, { "key": "ref17", "doi": "10.1145/3062341.3062387", "unstructured": "2017. Similarity of Binaries through re-optimization. In PLDI’17: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation" } ], "record": { "registrant": "Longman Publishers", "registered": "2026-09-07", "updated": "2026-09-20", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/161", "sha256_before": null, "sha256_after": "8f8febc7921ac57eca263ce4d531a92c17f970bd6df0d7d79a42b068a5b917bc" }, { "seq": 2, "kind": "update", "at": "2026-09-29 23:59:52", "by": "Administrator (admin)", "by_kind": "user", "note": "record re-read from api.crossref.org", "changes": [ { "path": "container.titles.0.value", "from": "Journal of Science & Technology", "to": "Journal of Science & Technology" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2018.v3.i06.pp59-67", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "DISTRIBUTED REPRESENTATIONS OF AWORD: A SURVEY", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2018.v3.i06.pp59-67" } ], "agents": [ { "role": "author", "name": { "given": "Mr.D.Koteswara", "family": "Rao" }, "sequence": "first" }, { "role": "author", "name": { "given": "Mr.T.Rathna", "family": "Kumar" }, "sequence": "additional" }, { "role": "author", "name": { "given": "Mrs.K.", "family": "Vineela" }, "sequence": "additional" }, { "role": "author", "name": { "given": "Mrs.B.Rama", "family": "Jyothi" }, "sequence": "additional" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2018-11-21", "date_type": "PublicationDate", "online": "2018-11-21" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "03", "issue": "06", "pages": { "first": "59", "last": "67" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/161", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/161/140", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/161/3446", "purpose": "text-mining", "return_type": "application/xml" }, { "url": "https://www.jst.org.in/index.php/pub/article/view/161/140", "purpose": "similarity-checking" } ], "abstract": { "value": "The continuous Skip-gram model, which was recently presented, is a quick and easy way to build high-quality distributed vector representations that capture a huge number of accurate syntactic and semantic word associations. We provide numerous enhancements in this study that improve the quality of the vectors as well as the training speed. We get a considerable speedup and learn more regular word representations by subsampling the frequent words. We also discuss negative sampling,which is a simple alternative to hierarchical softmax. The indifference to word order and inability to capture idiomatic phrases are two fundamental limitations of word representations. The meanings of \"Canada\" and \"Air,\" for example, cannot simply be merged to become \"Air Canada.", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2018-11-21", "applies_to": "vor" }, "references": [ { "key": "ref1", "doi": "10.1145/2635868.2635883", "unstructured": "MiltiadisAllamanis, Earl T. Barr, Christian Bird, and Charles Sutton. 2014. Learning Natural Coding Conventions. In Proceedings of the 22Nd ACM SIGSOFT International Symposium on Foundations of Software Engineering (FSE 2014). ACM, New York, NY, USA, 281ś293" }, { "key": "ref2", "doi": "10.1145/2635868.2635883", "unstructured": "https://doi.org/10.1145/2635868.2635883 MiltiadisAllamanis, Earl T. Barr, Christian Bird, and Charles Sutton. 2015a. Suggesting Accurate Method and Class Names. In Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering (ESEC/FSE 2015)" }, { "key": "ref3", "doi": "10.1145/2786805.2786849", "unstructured": "ACM, New York, NY, USA, 38ś49. https://doi.org/10.1145/2786805.2786849 MiltiadisAllamanis, Earl T Barr, PremkumarDevanbu, and Charles Sutton. 2017. A Survey of Machine Learning for Big Code and Naturalness. arXiv preprint arXiv:1709.06182 (2017)" }, { "key": "ref4", "unstructured": "MiltiadisAllamanis, Marc Brockschmidt, and Mahmoud Khademi. 2018. Learning to Represent Programs with Graphs. In ICLR. MiltiadisAllamanis, HaoPeng, and Charles A. Sutton. 2016. A Convolutional Attention Network for Extreme Summarization of Source Code" }, { "key": "ref5", "unstructured": "In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19- 24, 2016. 2091ś2100. http://jmlr.org/proceedings/papers/v48/allamanis16.html MiltiadisAllamanis and Charles Sutton" }, { "key": "ref6", "doi": "10.1109/msr.2013.6624029", "unstructured": "2013. Mining Source Code Repositories at Massive Scale Using Language Modeling. In Proceedings of the 10th Working Conference on Mining Software Repositories (MSR ’13). IEEE Press, Piscataway, NJ, USA, 207ś216" }, { "key": "ref7", "doi": "10.1145/2635868.2635901", "unstructured": "http://dl.acm.org/citation.cfm?id=2487085.2487127 MiltiadisAllamanis and Charles Sutton. 2014. Mining Idioms from Source Code. In Proceedings of the 22Nd ACM SIGSOFT International Symposium on Foundations of Software Engineering (FSE 2014). ACM, New York, NY, USA, 472ś483. https: //doi.org/10.1145/2635868.2635901 MiltiadisAllamanis, Daniel Tarlow, Andrew D. Gordon, and Yi Wei. 2015b. Bimodal Modelling of Source Code and Natural Language" }, { "key": "ref8", "unstructured": "In Proceedings of the 32nd International Conference on International Conference on Machine Learning-Volume 37 (ICML’15). JMLR.org, 2123ś2132. http://dl.acm.org/citation.cfm?id=3045118.3045344 Uri Alon, MeitalZilberstein, Omer Levy, and EranYahav. 2018. A General Path-based Representation for Predicting Program Properties" }, { "key": "ref9", "doi": "10.1145/3192366", "unstructured": "In Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2018). ACM, New York, NY, USA, 404ś419" }, { "key": "ref10", "unstructured": "Matthew Amodio, SwaratChaudhuri, and Thomas W. Reps. 2017. Neural Attribute Machines for Program Generation. CoRR abs/1705.09231 (2017). arXiv:1705.09231 http://arxiv.org/abs/1705.09231 Thierry Artieres et al" }, { "key": "ref11", "unstructured": "2010. Neural conditional random fields. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. 177ś184. Jimmy Ba, VolodymyrMnih, and KorayKavukcuoglu. 2014. Multiple object recognition with visual attention" }, { "key": "ref12", "unstructured": "arXiv preprint arXiv:1412.7755 (2014). DzmitryBahdanau, Kyunghyun Cho, and YoshuaBengio. 2014. Neural Machine Translation by Jointly Learning to Align and Translate. CoRR abs/1409.0473 (2014). http://arxiv.org/abs/1409.0473 DzmitryBahdanau, Jan Chorowski, DmitriySerdyuk, Philemon Brakel, and YoshuaBengio. 2016. End-to-end attentionbased large vocabulary speech recognition" }, { "key": "ref13", "doi": "10.1109/icassp.2003.1199851", "unstructured": "In Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE, 4945ś4949. YoshuaBengio, RéjeanDucharme, Pascal Vincent, and Christian Janvin. 2003. A Neural Probabilistic Language Model. J. Mach. Learn. Res. 3 (March 2003), 1137ś1155" }, { "key": "ref14", "unstructured": "http://dl.acm.org/citation.cfm?id=944919.944966 PavolBielik, VeselinRaychev, and Martin T. Vechev. 2016. PHOG: Probabilistic Model for Code. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016. 2933ś2942. http://jmlr.org/proceedings/papers/v48/bielik16.html Chris Callison-Burch, Miles Osborne, and Philipp Koehn. 2006. Re-evaluation the role of bleu in machine translation research" }, { "key": "ref15", "unstructured": "In 11th Conference of the European Chapter of the Association for Computational Linguistics. Jan KChorowski, DzmitryBahdanau, DmitriySerdyuk, Kyunghyun Cho, and YoshuaBengio. 2015. Attention-based models for speech recognition. In Advances in Neural Information Processing Systems. 577ś585. Ronan Collobert and Jason Weston" }, { "key": "ref16", "doi": "10.1145/1390156.1390177", "unstructured": "2008. A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. In Proceedings of the 25th International Conference on Machine Learning (ICML ’08). ACM, New York, NY, USA, 160ś167. https://doi.org/10.1145/1390156.1390177 Yaniv David, Nimrod Partush, and EranYahav. 2016. Statistical Similarity in Binaries. In PLDI’16: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation. Yaniv David, Nimrod Partush, and EranYahav" }, { "key": "ref17", "doi": "10.1145/3062341.3062387", "unstructured": "2017. Similarity of Binaries through re-optimization. In PLDI’17: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation" } ], "record": { "registrant": "Longman Publishers", "registered": "2026-09-07", "updated": "2026-09-20", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/161", "sha256_before": "8f8febc7921ac57eca263ce4d531a92c17f970bd6df0d7d79a42b068a5b917bc", "sha256_after": "f4023c9570fa12c75a539fe3aa15c551f800a2197d98830634f568590228e7c1" } ] }