{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T01:19:35Z","timestamp":1777339175696,"version":"3.51.4"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,4,20]],"date-time":"2018-04-20T00:00:00Z","timestamp":1524182400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,4,20]],"date-time":"2018-04-20T00:00:00Z","timestamp":1524182400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Digit Libr"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s00799-018-0237-y","type":"journal-article","created":{"date-parts":[[2018,4,20]],"date-time":"2018-04-20T16:09:47Z","timestamp":1524240587000},"page":"109-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Toward meaningful notions of similarity in NLP embedding models"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3538-9469","authenticated-orcid":false,"given":"\u00c1bel","family":"Elekes","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Englhardt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Sch\u00e4ler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Klemens","family":"B\u00f6hm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,4,20]]},"reference":[{"key":"237_CR1","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1002\/lnco.362","volume":"6","author":"K Erk","year":"2012","unstructured":"Erk, K.: Vector space models of word meaning and phrase meaning: a survey. Language and Linguistics Compass 6, 635\u2013653 (2012)","journal-title":"Language and Linguistics Compass"},{"key":"237_CR2","first-page":"493","volume-title":"Vector Space Models of Lexical Meaning. Handbook of Contemporary Semantic Theory","author":"S Clark","year":"2013","unstructured":"Clark, S.: Vector Space Models of Lexical Meaning. Handbook of Contemporary Semantic Theory, pp. 493\u2013522. Wiley, London (2013)"},{"key":"237_CR3","doi-asserted-by":"crossref","unstructured":"Baroni, M., Dinu, G., Kruszewski, G.: Don\u2019t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors. In: ACL, vol. 1 (2014)","DOI":"10.3115\/v1\/P14-1023"},{"key":"237_CR4","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"S Deerwester","year":"1990","unstructured":"Deerwester, S., Dumais, S.T., Furnas, G.W., Landauer, T.K., Harshman, R.: Indexing by latent semantic analysis. J. Am. Soc. Inf. Sci. 41, 391 (1990)","journal-title":"J. Am. Soc. Inf. Sci."},{"key":"237_CR5","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"237_CR6","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137\u20131155 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"237_CR7","first-page":"2493","volume":"12","author":"R Collobert","year":"2011","unstructured":"Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493\u20132537 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"237_CR8","doi-asserted-by":"crossref","unstructured":"Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning (2008)","DOI":"10.1145\/1390156.1390177"},{"key":"237_CR9","unstructured":"Huang, E.H., Socher, R., Manning, C.D., Ng, A.Y.: Improving word representations via global context and multiple word prototypes. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers, vol. 1 (2012)"},{"key":"237_CR10","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"237_CR11","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. (2013). arXiv:1301.3781"},{"key":"237_CR12","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems (2013)"},{"key":"237_CR13","unstructured":"Passos, A., Kumar, V., McCallum, A.: Lexicon infused phrase embeddings for named entity resolution (2014). arXiv:1404.5367"},{"key":"237_CR14","unstructured":"Komatsu, H., Tian, R., Okazaki, N., Inui, K.: Reducing lexical features in parsing by word embeddings. In: Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (2015)"},{"key":"237_CR15","doi-asserted-by":"crossref","unstructured":"Wang, W.Y., Yang, D.: That\u2019s so annoying!!!: a lexical and frame-semantic embedding based data augmentation approach to automatic categorization of annoying behaviors using petpeeve tweets. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), Lisbon, Portugal (2015)","DOI":"10.18653\/v1\/D15-1306"},{"key":"237_CR16","unstructured":"Klein, B., Lev, G., Sadeh, G., Wolf, L.: Fisher vectors derived from hybrid Gaussian\u2013Laplacian mixture models for image annotation (2014). arXiv:1411.7399"},{"key":"237_CR17","doi-asserted-by":"crossref","unstructured":"Devlin, J., Zbib, R., Huang, Z., Lamar, T., Schwartz, R.M., Makhoul, J.: Fast and robust neural network joint models for statistical machine translation. In: ACL, vol. 1 (2014)","DOI":"10.3115\/v1\/P14-1129"},{"key":"237_CR18","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems (2014)"},{"key":"237_CR19","doi-asserted-by":"crossref","unstructured":"Liu, S., Yang, N., Li, M., Zhou, M.: A recursive recurrent neural network for statistical machine translation. In: ACL, vol. 1 (2014)","DOI":"10.3115\/v1\/P14-1140"},{"key":"237_CR20","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1162\/tacl_a_00134","volume":"3","author":"O Levy","year":"2015","unstructured":"Levy, O., Goldberg, Y., Dagan, I.: Improving distributional similarity with lessons learned from word embeddings. Trans. Assoc. Comput. Linguist. 3, 211\u2013225 (2015)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"237_CR21","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-319-18111-0_31","volume-title":"Computational Linguistics and Intelligent Text Processing","author":"R\u00e9mi Lebret","year":"2015","unstructured":"Lebret, R., Collobert, R.: Rehabilitation of count-based models for word vector representations. In: International Conference on Intelligent Text Processing and Computational Linguistics (2015)"},{"key":"237_CR22","unstructured":"Hill, F., Cho, K., Jean, S., Devin, C., Bengio, Y.: Not all neural embeddings are born equal (2014). arXiv:1410.0718"},{"key":"237_CR23","doi-asserted-by":"crossref","unstructured":"Schnabel, T., Labutov, I., Mimno, D., Joachims, T.: Evaluation methods for unsupervised word embeddings. In: Proceedings of EMNLP (2015)","DOI":"10.18653\/v1\/D15-1036"},{"key":"237_CR24","doi-asserted-by":"crossref","unstructured":"Finkelstein, L., Gabrilovich, E., Matias, Y., Rivlin, E., Solan, Z., Wolfman, G., Ruppin, E.: Placing search in context: the concept revisited. In: Proceedings of the 10th International Conference on World Wide Web (2001)","DOI":"10.1145\/371920.372094"},{"key":"237_CR25","unstructured":"Bruni, E., Boleda, G., Baroni, M., Tran, N.-K.: Distributional semantics in technicolor. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers, vol. 1 (2012)"},{"key":"237_CR26","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1162\/COLI_a_00237","volume":"41","author":"F Hill","year":"2016","unstructured":"Hill, F., Reichart, R., Korhonen, A.: Simlex-999: evaluating semantic models with (genuine) similarity estimation. Comput. Linguist. 41, 665\u2013695 (2016)","journal-title":"Comput. Linguist."},{"key":"237_CR27","doi-asserted-by":"crossref","unstructured":"Batchkarov, M., Kober, T., Reffin, J., Weeds, J., Weir, D.: A critique of word similarity as a method for evaluating distributional semantic models. In: Proceedings of the 1st Workshop on Evaluating Vector Space Representations for NLP (2016)","DOI":"10.18653\/v1\/W16-2502"},{"key":"237_CR28","unstructured":"Avraham, O., Goldberg, Y.: Improving reliability of word similarity evaluation by redesigning annotation task and performance measure (2016). arXiv:1611.03641"},{"key":"237_CR29","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38, 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"237_CR30","doi-asserted-by":"crossref","unstructured":"Elekes, A., Sch\u00e4ler, M., Boehm, K.: On the various semantics of similarity in word embedding models. In: 2017 ACM\/IEEE Joint Conference on Digital Libraries (JCDL) (2017)","DOI":"10.1109\/JCDL.2017.7991568"},{"key":"237_CR31","unstructured":"Levy, O., Goldberg, Y.: Neural word embedding as implicit matrix factorization. In: Advances in Neural Information Processing Systems (2014)"},{"key":"237_CR32","unstructured":"Shi, T., Liu, Z.: Linking GloVe with word2vec (2014). arXiv:1411.5595"},{"key":"237_CR33","unstructured":"Rehurek, R., Sojka, P.: Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks (2010)"},{"key":"237_CR34","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information (2016). arXiv:1607.04606"},{"key":"237_CR35","unstructured":"Miura, Y., Taniguchi, M., Taniguchi,T., Ohkuma, T.: A simple scalable neural networks based model for geolocation prediction in Twitter. In: WNUT 2016, vol. 9026924, p. 235 (2016)"},{"key":"237_CR36","unstructured":"Seo, S., Huang, J., Yang, H., Liu, Y.: Representation learning of users and items for review rating prediction using attention-based convolutional neural network. In: 3rd International Workshop on Machine Learning Methods for Recommender Systems (MLRec)(SDM\u201917) (2017)"},{"key":"237_CR37","unstructured":"Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: Proceedings of the 31st International Conference on Machine Learning (ICML-14) (2014)"},{"key":"237_CR38","doi-asserted-by":"crossref","unstructured":"Badjatiya, P., Gupta, S., Gupta, M., Varma, V.: Deep learning for hate speech detection in tweets. In: Proceedings of the 26th International Conference on World Wide Web Companion (2017)","DOI":"10.1145\/3041021.3054223"},{"key":"237_CR39","unstructured":"Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification (2016). arXiv:1607.01759"},{"key":"237_CR40","unstructured":"Kusner, M., Sun, Y., Kolkin, N., Weinberger, K.: From word embeddings to document distances. In: International Conference on Machine Learning (2015)"},{"key":"237_CR41","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1080\/01621459.1951.10500769","volume":"46","author":"FJ Massey Jr","year":"1951","unstructured":"Massey Jr., F.J.: The Kolmogorov\u2013Smirnov test for goodness of fit. J. Am. Stat. Assoc. 46, 68\u201378 (1951)","journal-title":"J. Am. Stat. Assoc."},{"key":"237_CR42","unstructured":"Chelba, C., Mikolov, T., Schuster, M., Ge, Q., Brants, T., Koehn, P., Robinson, T.: One billion word benchmark for measuring progress in statistical language modeling (2013). arXiv:1312.3005"},{"key":"237_CR43","first-page":"1","volume":"2016","author":"B Chiu","year":"2016","unstructured":"Chiu, B., Korhonen, A., Pyysalo, S.: Intrinsic evaluation of word vectors fails to predict extrinsic performance. ACL 2016, 1 (2016)","journal-title":"ACL"},{"key":"237_CR44","unstructured":"Rong, X.: word2vec parameter learning explained (2014). arXiv:1411.2738"},{"key":"237_CR45","unstructured":"Altszyler, E., Sigman, M., Slezak, D.F.: Comparative study of LSA vs Word2vec embeddings in small corpora: a case study in dreams database (2016). arXiv:1610.01520"},{"key":"237_CR46","unstructured":"Lin, C.-C., Ammar, W., Dyer, C., Levin, L.: Unsupervised POS induction with word embeddings (2015). arXiv:1503.06760"},{"key":"237_CR47","doi-asserted-by":"crossref","unstructured":"Leacock, C., Chodorow, M.: Combining local context and WordNet similarity for word sense identification. WordNet: An Electronic Lexical Database, vol. 49, pp. 265\u2013283 (1998)","DOI":"10.7551\/mitpress\/7287.003.0018"},{"key":"237_CR48","unstructured":"Mihalcea, R., Corley, C., Strapparava, C.: Corpus-based and knowledge-based measures of text semantic similarity. In: AAAI (2006)"},{"key":"237_CR49","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1162\/coli.2006.32.1.13","volume":"32","author":"A Budanitsky","year":"2006","unstructured":"Budanitsky, A., Hirst, G.: Evaluating wordnet-based measures of lexical semantic relatedness. Comput. Linguist. 32, 13\u201347 (2006)","journal-title":"Comput. Linguist."},{"key":"237_CR50","unstructured":"Budanitsky, A., Hirst, G.: Semantic distance in WordNet: an experimental, application-oriented evaluation of five measures. In: Workshop on WordNet and Other Lexical Resources (2001)"},{"key":"237_CR51","first-page":"1","volume":"6","author":"L Meng","year":"2013","unstructured":"Meng, L., Huang, R., Gu, J.: A review of semantic similarity measures in wordnet. Int. Hybrid Inf. Technol. 6, 1\u201312 (2013)","journal-title":"Int. Hybrid Inf. Technol."},{"key":"237_CR52","doi-asserted-by":"crossref","unstructured":"Bird, S.: NLTK: the natural language toolkit. In: Proceedings of the COLING\/ACL on Interactive Presentation Sessions (2006)","DOI":"10.3115\/1225403.1225421"},{"key":"237_CR53","first-page":"28","volume":"34","author":"BL Welch","year":"1947","unstructured":"Welch, B.L.: The generalization of Student\u2019s\u2019 problem when several different population variances are involved. Biometrika 34, 28\u201335 (1947)","journal-title":"Biometrika"},{"key":"237_CR54","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1126\/science.1199644","volume":"331","author":"J-B Michel","year":"2011","unstructured":"Michel, J.-B., Shen, Y.K., Aiden, A.P., Veres, A., Gray, M.K., Pickett, J.P., Hoiberg, D., Clancy, D., Norvig, P., Orwant, J., et al.: Quantitative analysis of culture using millions of digitized books. Science 331, 176\u2013182 (2011)","journal-title":"Science"},{"key":"237_CR55","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1145\/365628.365657","volume":"8","author":"H Rubenstein","year":"1965","unstructured":"Rubenstein, H., Goodenough, J.B.: Contextual correlates of synonymy. Commun. ACM 8, 627\u2013633 (1965)","journal-title":"Commun. ACM"},{"key":"237_CR56","doi-asserted-by":"crossref","unstructured":"Radinsky, K., Agichtein, E., Gabrilovich, E., Markovitch, S.: A word at a time: computing word relatedness using temporal semantic analysis. In: Proceedings of the 20th International Conference On World Wide Web (2011)","DOI":"10.1145\/1963405.1963455"},{"key":"237_CR57","unstructured":"Luong, T., Socher, R., Manning, C.D.: Better word representations with recursive neural networks for morphology. In: CoNLL (2013)"}],"container-title":["International Journal on Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-018-0237-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00799-018-0237-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-018-0237-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T05:46:40Z","timestamp":1720244800000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00799-018-0237-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,20]]},"references-count":57,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["237"],"URL":"https:\/\/doi.org\/10.1007\/s00799-018-0237-y","relation":{},"ISSN":["1432-5012","1432-1300"],"issn-type":[{"value":"1432-5012","type":"print"},{"value":"1432-1300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4,20]]},"assertion":[{"value":"15 September 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}