{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:10:06Z","timestamp":1750212606826,"version":"3.41.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2017,4,29]],"date-time":"2017-04-29T00:00:00Z","timestamp":1493424000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Translation"],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1007\/s10590-017-9194-2","type":"journal-article","created":{"date-parts":[[2017,4,29]],"date-time":"2017-04-29T13:13:26Z","timestamp":1493471606000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["The representational geometry of word meanings acquired by neural machine translation models"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6712-1718","authenticated-orcid":false,"given":"Felix","family":"Hill","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyunghyun","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00e9bastien","family":"Jean","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshua","family":"Bengio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,4,29]]},"reference":[{"key":"9194_CR1","doi-asserted-by":"crossref","unstructured":"Agirre E, Alfonseca E, Hall K, Kravalova J, Pasca M, Soroa A (2009) A study on similarity and relatedness using distributional and wordnet-based approaches. In: Proceedings of NAACL-HLT 2009","DOI":"10.3115\/1620754.1620758"},{"key":"9194_CR2","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: Proceedings of ICLR"},{"key":"9194_CR3","doi-asserted-by":"crossref","unstructured":"Baroni M, Dinu G, Kruszewski G (2014) Dont count, predict! a systematic comparison of context-counting vs. context-predicting semantic vectors. In: Proceedings of the 52nd annual meeting of the association for computational linguistics, vol 1","DOI":"10.3115\/v1\/P14-1023"},{"key":"9194_CR4","unstructured":"Bengio Y, S\u00e9n\u00e9cal JS (2003) Quick training of probabilistic neural nets by importance sampling. In: Proceedings of AISTATS 2003"},{"key":"9194_CR5","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio Y, Ducharme R, Vincent P, Janvin C (2003) A neural probabilistic language model. J Mach Learn Res 3:1137\u20131155","journal-title":"J Mach Learn Res"},{"key":"9194_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.4135","volume":"49","author":"E Bruni","year":"2014","unstructured":"Bruni E, Tran NK, Baroni M (2014) Multimodal distributional semantics. J Artif Intell Res(JAIR) 49:1\u201347","journal-title":"J Artif Intell Res(JAIR)"},{"key":"9194_CR7","unstructured":"Chandar S, Lauly S, Larochelle H, Khapra MM, Ravindran B, Raykar V, Saha A (2014) An autoencoder approach to learning bilingual word representations. In: NIPS"},{"key":"9194_CR8","doi-asserted-by":"crossref","unstructured":"Cho K, van Merrienboer B, Gulcehre C, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the empirical methods in natural language processing (EMNLP 2014), to appear","DOI":"10.3115\/v1\/D14-1179"},{"key":"9194_CR9","doi-asserted-by":"crossref","unstructured":"Collobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th international conference on machine learning, ACM, pp 160\u2013167","DOI":"10.1145\/1390156.1390177"},{"key":"9194_CR10","first-page":"2493","volume":"12","author":"R Collobert","year":"2011","unstructured":"Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa P (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12:2493\u20132537","journal-title":"J Mach Learn Res"},{"key":"9194_CR11","doi-asserted-by":"crossref","unstructured":"Devlin J, Zbib R, Huang Z, Lamar T, Schwartz R, Makhoul J (2014) Fast and robust neural network joint models for statistical machine translation. In: 52nd annual meeting of the association for computational linguistics, Baltimore, June","DOI":"10.3115\/v1\/P14-1129"},{"key":"9194_CR12","doi-asserted-by":"crossref","unstructured":"Faruqui M, Dyer C (2014) Improving vector space word representations using multilingual correlation. In: Proceedings of EACL, vol 2014","DOI":"10.3115\/v1\/E14-1049"},{"key":"9194_CR13","first-page":"1","volume-title":"A synopsis of linguistic theory 1930\u20131955","author":"RJ Firth","year":"1957","unstructured":"Firth RJ (1957) A synopsis of linguistic theory 1930\u20131955. Philological Society, Oxford, pp 1\u201332"},{"key":"9194_CR14","unstructured":"Haghighi A, Liang P, Berg-Kirkpatrick T, Klein D (2008) Learning bilingual lexicons from monolingual corpora. In: ACL, vol 2008, pp 771\u2013779"},{"key":"9194_CR15","unstructured":"Hermann KM, Blunsom P (2014) Multilingual distributed representations without word alignment. In: Proceedings of ICLR"},{"key":"9194_CR16","doi-asserted-by":"crossref","unstructured":"Hill F, Korhonen A (2014) Learning abstract concepts from multi-modal data: since you probably can\u2019t see what i mean. In: Proceedings of the empirical methods in natural language processing (EMNLP 2014)","DOI":"10.3115\/v1\/D14-1032"},{"key":"9194_CR17","unstructured":"Hill F, Reichart R, Korhonen A (2014) Simlex-999: evaluating semantic models with (genuine) similarity estimation. arXiv preprint arXiv:1408.3456"},{"key":"9194_CR18","doi-asserted-by":"crossref","unstructured":"Jean S, Cho K, Memisevic R, Bengio Y (2015) On using very large target vocabulary for neural machine translation. In: Proceedings of NAACL","DOI":"10.3115\/v1\/P15-1001"},{"key":"9194_CR19","doi-asserted-by":"crossref","unstructured":"Kalchbrenner N, Blunsom P (2013) Recurrent continuous translation models. In: Proceedings of the 2013 conference on empirical methods in natural language processing, Association for Computational Linguistics, Seattle","DOI":"10.18653\/v1\/D13-1176"},{"key":"9194_CR20","unstructured":"Klementiev A, Titov I, Bhattarai B (2012a) Inducing crosslingual distributed representations of words. COLING"},{"key":"9194_CR21","unstructured":"Klementiev A, Titov I, Bhattarai B (2012b) Inducing crosslingual distributed representations of words. In: COLING"},{"key":"9194_CR22","doi-asserted-by":"crossref","unstructured":"Ko\u010disk\u00fd T, Hermann KM, Blunsom P (2014) Learning bilingual word representations by marginalizing alignments. In: Proceedings of ACL","DOI":"10.3115\/v1\/P14-2037"},{"key":"9194_CR23","unstructured":"Kusner M, Sun Y, Kolkin N, Weinberger KQ (2015) From word embeddings to document distances. In: Proceedings of the 32nd international conference on machine learning (ICML-15), pp 957\u2013966"},{"issue":"2","key":"9194_CR24","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1037\/0033-295X.104.2.211","volume":"104","author":"TK Landauer","year":"1997","unstructured":"Landauer TK, Dumais ST (1997) A solution to plato\u2019s problem: the latent semantic analysis theory of acquisition, induction, and representation of knowledge. Psychol Rev 104(2):211","journal-title":"Psychol Rev"},{"key":"9194_CR25","doi-asserted-by":"crossref","unstructured":"Levy O, Goldberg Y (2014) Dependency-based word embeddings. In: Proceedings of the 52nd annual meeting of the association for computational linguistics, vol 2","DOI":"10.3115\/v1\/P14-2050"},{"key":"9194_CR26","unstructured":"Luong T, Sutskever I, Le QV, Vinyals O, Zaremba W (2014) Addressing the rare word problem in neural machine translation. arXiv preprint arXiv:1410.8206"},{"key":"9194_CR27","unstructured":"Mikolov T, Le QV, Sutskever I (2013a) Exploiting similarities among languages for machine translation. In: CORR"},{"key":"9194_CR28","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013b) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111\u20133119"},{"key":"9194_CR29","unstructured":"Mnih A, Hinton GE (2009) A scalable hierarchical distributed language model. In: Advances in neural information processing systems, pp 1081\u20131088"},{"key":"9194_CR30","first-page":"246","volume":"5","author":"F Morin","year":"2005","unstructured":"Morin F, Bengio Y (2005) Hierarchical probabilistic neural network language model. AISTATS, Citeseer 5:246\u2013252","journal-title":"AISTATS, Citeseer"},{"issue":"3","key":"9194_CR31","doi-asserted-by":"crossref","first-page":"402","DOI":"10.3758\/BF03195588","volume":"36","author":"DL Nelson","year":"2004","unstructured":"Nelson DL, McEvoy CL, Schreiber TA (2004) The university of south florida free association, rhyme, and word fragment norms. Behav Res Methods Instrum Comput 36(3):402\u2013407","journal-title":"Behav Res Methods Instrum Comput"},{"key":"9194_CR32","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: Proceedings of the empirical methods in natural language processing (EMNLP 2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"9194_CR33","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Proceedings of NIPS"},{"issue":"1","key":"9194_CR34","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1613\/jair.2934","volume":"37","author":"PD Turney","year":"2010","unstructured":"Turney PD, Pantel P (2010) From frequency to meaning: vector space models of semantics. J Artif Intell Res 37(1):141\u2013188","journal-title":"J Artif Intell Res"},{"key":"9194_CR35","unstructured":"Vuli\u0107 I, De\u00a0Smet W, Moens MF (2011) Identifying word translations from comparable corpora using latent topic models. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies: short papers, Vol 2, Association for Computational Linguistics, pp 479\u2013484"},{"issue":"1","key":"9194_CR36","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s10994-010-5198-3","volume":"81","author":"J Weston","year":"2010","unstructured":"Weston J, Bengio S, Usunier N (2010) Large scale image annotation: learning to rank with joint word-image embeddings. Mach Learn 81(1):21\u201335","journal-title":"Mach Learn"}],"container-title":["Machine Translation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10590-017-9194-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-017-9194-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-017-9194-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:42:04Z","timestamp":1750210924000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10590-017-9194-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,29]]},"references-count":36,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2017,6]]}},"alternative-id":["9194"],"URL":"https:\/\/doi.org\/10.1007\/s10590-017-9194-2","relation":{},"ISSN":["0922-6567","1573-0573"],"issn-type":[{"type":"print","value":"0922-6567"},{"type":"electronic","value":"1573-0573"}],"subject":[],"published":{"date-parts":[[2017,4,29]]}}}