{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:10:01Z","timestamp":1748718601924,"version":"3.41.0"},"publisher-location":"Cham","reference-count":97,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319254845"},{"type":"electronic","value":"9783319254852"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-25485-2_5","type":"book-chapter","created":{"date-parts":[[2015,12,9]],"date-time":"2015-12-09T15:29:25Z","timestamp":1449674965000},"page":"185-228","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Web as a Corpus: Going Beyond the n-gram"],"prefix":"10.1007","author":[{"given":"Preslav","family":"Nakov","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,12,10]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Rajeev, A., Boggess, L.: A simple but useful approach to conjunct identification. In: Proceedings of ACL, pp. 15\u201321 (1992)","DOI":"10.3115\/981967.981970"},{"key":"5_CR2","unstructured":"Michele, B., Brill, E.: Scaling to very very large corpora for natural language disambiguation. In: Proceedings of ACL (2001)"},{"key":"5_CR3","unstructured":"Bansal, M., Klein, D.: Web-scale features for full-scale parsing. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - vol.1, HLT 2011, pp. 693\u2013702. PA, USA, Stroudsburg (2011)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Barker, K., Szpakowicz, S.: Semi-automatic recognition of noun modifier relationships. In: Proceedings of the 17th international conference on Computational linguistics, 96\u2013102. Association for Computational Linguistics, Morristown, NJ, USA (1998)","DOI":"10.3115\/980451.980862"},{"key":"5_CR5","unstructured":"Bergsma, S., Goebel, R.: Using visual information to predict lexical preference. In: Proceedings of the International Conference Recent Advances in Natural Language Processing 2011, pp. 399\u2013405. RANLP 2011 Organising Committee, Hissar, Bulgaria (2011)"},{"key":"5_CR6","unstructured":"Pitler, E., Lin, D.: Creating robust supervised classifiers via web-scale n-gram data. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 865\u2013874. Uppsala, Sweden (2010)"},{"key":"5_CR7","unstructured":"Van Durme, B.: Learning bilingual lexicons using the visual similarity of labeled web images. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence -Volume Volume Three, IJCAI 2011, pp. 1764\u20131769. AAAI Press (2011)"},{"key":"5_CR8","unstructured":"Iris Wang, Q.: Learning noun phrase query segmentation. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 819\u2013826 (2007)"},{"key":"5_CR9","unstructured":"Brants, T., Popat, A.C., Peng, X., Och, F.J., Dean, J.: Large language models in machine translation. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 858\u2013867. Czech Republic, Prague (2007)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Brill, E., Resnik, P.: A rule-based approach to prepositional phrase attachment disambiguation. In: Proceedings of COLING (1994)","DOI":"10.3115\/991250.991346"},{"key":"5_CR11","first-page":"107","volume":"30","author":"S Brin","year":"1998","unstructured":"Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. Comput. Netw. 30, 107\u2013117 (1998)","journal-title":"Comput. Netw."},{"key":"5_CR12","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":"5_CR13","unstructured":"Butnariu, C., Kim, SN., Nakov, P., S\u00e9aghdha, D., Szpakowicz, S., Veale, T.: Noun compounds using paraphrasing verbs and prepositions. In: Proceedings of the 5th International Workshop on Semantic Evaluations (SemEval-2), Uppsala, Sweden, 11\u201316 July 2010, pp. 39\u201344 (2010)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Veale, T.: A concept-centered approach to noun-compound interpretation. In: Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pp. 81\u201388. Manchester, UK (2008)","DOI":"10.3115\/1599081.1599092"},{"key":"5_CR15","unstructured":"Cafarella, M., Banko, M., Etzioni, O.: Technical Report 02 April 2006, University of Washington, Department of Computer Science and Engineering (2006)"},{"key":"5_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1007\/978-3-540-24586-5_74","volume-title":"Progress in Pattern Recognition, Speech and Image Analysis","author":"H Calvo","year":"2003","unstructured":"Calvo, H., Gelbukh, A.: Improving prepositional phrase attachment disambiguation using the web as corpus. In: Sanfeliu, A., Ruiz-Shulcloper, J. (eds.) CIARP 2003. LNCS, vol. 2905, pp. 604\u2013610. Springer, Heidelberg (2003)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Cao, Y., Li, H.: Base noun phrase translation using web data and the EM algorithm. In: COLING, pp. 127\u2013133 (2002)","DOI":"10.3115\/1072228.1072239"},{"key":"5_CR18","unstructured":"Chantree, F., Kilgarriff, A., De Roeck, A., Willis, A.: Using a distributional thesaurus to resolve coordination ambiguities. In: Technical Report 2005\/02. The Open University, UK (2005)"},{"key":"5_CR19","unstructured":"Chklovski, T., Pantel, P.: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 33\u201340 (2004)"},{"key":"5_CR20","first-page":"139","volume":"8","author":"K Church","year":"1982","unstructured":"Church, K., Patil, R.: Coping with syntactic ambiguity or how to put the block in the box on the table. Am. J. Comput. Linguist. 8, 139\u2013149 (1982)","journal-title":"Am. J. Comput. Linguist."},{"key":"5_CR21","unstructured":"Collins, M., Brooks, J.: Prepositional phrase attachment through a backed-off model. In: Proceedings of EMNLP, pp. 27\u201338 (1995)"},{"issue":"4","key":"5_CR22","doi-asserted-by":"publisher","first-page":"810","DOI":"10.2307\/412913","volume":"53","author":"P Downing","year":"1977","unstructured":"Downing, P.: On the creation and use of english compound nouns. Language 53(4), 810\u2013842 (1977)","journal-title":"Language"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Dumais, S., Banko, M., Brill, E., Lin, J., Andrew Ng.: Web question answering: Is more always better?. In: Proceedings of SIGIR, pp. 291\u2013298 (2002)","DOI":"10.1145\/564376.564428"},{"key":"5_CR24","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001","volume-title":"Wordnet: An Electronic Lexical Database","author":"C Fellbaum","year":"1998","unstructured":"Fellbaum, C.: Wordnet: An Electronic Lexical Database. MIT Press, Cambridge (1998)"},{"key":"5_CR25","volume-title":"Statistical Methods for Rates and Proportions","author":"JL Fleiss","year":"1981","unstructured":"Fleiss, J.L.: Statistical Methods for Rates and Proportions, 2nd edn. John Wiley & Sons Inc, New York (1981)","edition":"2"},{"issue":"4","key":"5_CR26","first-page":"479","volume":"19","author":"R Girju","year":"2005","unstructured":"Girju, R., Moldovan, D., Tatu, M., Antohe, D.: On the semantics of noun compounds. Special Issue on Multiword Expressions 19(4), 479\u2013496 (2005)","journal-title":"Special Issue on Multiword Expressions"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Girju, R., Nakov, P., Nastase, Szpakowicz, S., Turney, P., Yuret. D.: Semeval-2007 task 04: classification of semantic relations between nominals. In: Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), pp. 13\u201318, Prague, Czech Republic (2007)","DOI":"10.3115\/1621474.1621477"},{"key":"5_CR28","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s10579-009-9083-2","volume":"43","author":"P Nakov","year":"2009","unstructured":"Nakov, P., Nastase, V., Szpakowicz, S., Turney, P., Yuret, D.: Language Resources and Evaluation 43, 105\u2013121 (2009)","journal-title":"Language Resources and Evaluation"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Goldberg, M.: An unsupervised model for statistically determining coordinate phrase attachment. In: Proceedings of ACL, pp. 610\u2013614 (1999)","DOI":"10.3115\/1034678.1034690"},{"key":"5_CR30","unstructured":"Grefenstette, G.: The world wide web as a resourcefor example-based machine translation tasks. In: Proceedings of the ASLIB Conference on Translating and the Computer (1998)"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Hendrickx, I., Kim, S.N., Kozareva, Z., Nakov, P., S\u00e9aghdha, D., Pad\u00f3, S., Romano, M., Szpakowicz, S.: SemEval-2010 Task 8: Multi-way classification of semantic relations between pairs of nominals. In: Proceedings of the 5th International Workshop on Semantic Evaluations (SemEval-2), Uppsala, Sweden, 11\u2013 16 July 2010, 33\u201338 (2010)","DOI":"10.3115\/1621969.1621986"},{"key":"5_CR32","series-title":"Lecture Notes in Business Information Processing","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-05085-5","volume-title":"Semantic Methods for Execution-level Business Process Modeling: Modeling Support Through Process Verification and Service Composition","author":"IM Weber","year":"2009","unstructured":"Weber, I.M.: Semantic Methods for Execution-level Business Process Modeling. LNBIP, vol. 40. Springer, Heidelberg (2009)"},{"key":"5_CR33","first-page":"103","volume":"19","author":"D Hindle","year":"1993","unstructured":"Hindle, D., Rooth, M.: Structural ambiguity and lexical relations. Comput. Linguist. 19, 103\u2013120 (1993)","journal-title":"Comput. Linguist."},{"key":"5_CR34","unstructured":"Szpektor, I., Tanev, H., Dagan, I., Coppola, B.: Scaling web-based acquisition of entailment relations. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 401\u201348 (2004)"},{"key":"5_CR35","series-title":"Lecture Notes in Business Information Processing","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/978-3-642-05085-5_6","volume-title":"Semantic Methods for Execution-level Business Process Modeling","author":"IM Weber","year":"2009","unstructured":"Weber, I.M.: Evaluation. Semantic Methods for Execution-level Business Process Modeling. LNBIP, vol. 40, pp. 203\u2013225. Springer, Heidelberg (2009)"},{"key":"5_CR36","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1162\/089120103322711604","volume":"29","author":"F Keller","year":"2003","unstructured":"Keller, F., Lapata, M.: Using the Web to obtain frequencies for unseen bigrams. Comput. Linguist. 29, 459\u2013484 (2003)","journal-title":"Comput. Linguist."},{"key":"5_CR37","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1162\/089120103322711569","volume":"29","author":"A Kilgariff","year":"2003","unstructured":"Kilgariff, A., Grefenstette, G.: Introduction to the special issue on the web as corpus. Comput. Linguist. 29, 333\u2013347 (2003)","journal-title":"Comput. Linguist."},{"key":"5_CR38","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1162\/coli.2007.33.1.147","volume":"33","author":"A Kilgarriff","year":"2007","unstructured":"Kilgarriff, A.: Googleology is bad science. Comput. Linguist. 33, 147\u2013151 (2007)","journal-title":"Comput. Linguist."},{"key":"5_CR39","unstructured":"Nam, K.S., Nakov, P.: Large-scale noun compound interpretation using bootstrapping and the web as a corpus. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pp. 648\u2013658. Edinburgh, Scotland, UK (2011)"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Kurohashi, S., Nagao, M.: Dynamic programming method for analyzing conjunctive structures in Japanese. In: Proceedings of COLING, vol. 1 (1992)","DOI":"10.3115\/992066.992095"},{"key":"5_CR41","unstructured":"Lapata, M., Keller, F.: The Web as a baseline: evaluating the performance of unsupervised Web-based models for a range of NLP tasks. In: Proceedings of HLT-NAACL, pp. 121\u2013128, Boston (2004)"},{"issue":"1","key":"5_CR42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1075389.1075390","volume":"2","author":"F Keller","year":"2005","unstructured":"Keller, F.: Web-based models for natural language processing. ACM Trans. Speech Lang. Process. 2(1), 1\u201331 (2005)","journal-title":"ACM Trans. Speech Lang. Process."},{"key":"5_CR43","unstructured":"Lauer, M.: Designing statistical language learners: experiments on noun compounds. Department of Computing Macquarie University NSW 2109 Australia dissertation (1995)"},{"key":"5_CR44","volume-title":"The syntax and semantics of complex nominals","author":"J Levi","year":"1978","unstructured":"Levi, J.: The syntax and semantics of complex nominals. Academic Press, New York (1978)"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Levy, O., Goldberg, Y.: Linguistic regularities in sparse and explicit word representations. In: Proceedings of the Eighteenth Conference on Computational Natural Language Learning, 171\u2013180 (2014)","DOI":"10.3115\/v1\/W14-1618"},{"key":"5_CR46","unstructured":"Lin, D.: An information-theoretic definition of similarity. In: ICML 1998: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 296\u2013304. Morgan Kaufmann Publishers Inc San Francisco, CA, USA (1998)"},{"key":"5_CR47","unstructured":"Church, K., Ji, H., Sekine, S., Yarowsky, D., Bergsma, S., Patil, K., Pitler, E., Lathbury, R., Rao, V., Dalwani, K., Narsale, S.: New tools for web-scale n-grams. In: Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC 2010) Calzolari, N., (Conference Chair), Choukri, K., Maegaard, B., Mariani, J., Odijk, J., Piperidis, S., Rosner, M.,Tapias, D., Valletta, M.: European Language Resources Association (ELRA) (2010)"},{"key":"5_CR48","unstructured":"Lin, Y., Michel, J.-B., Lieberman, E.A., Orwant, J., Brockman, W., Petrov, S.: Syntactic annotations for the google books ngram corpus. In: Proceedings of the ACL 2012 System Demonstrations, pp. 169\u2013174. Jeju Island, Korea (2012)"},{"key":"5_CR49","volume-title":"A Theory of Syntactic Recognition for Natural Language","author":"M Marcus","year":"1980","unstructured":"Marcus, M.: A Theory of Syntactic Recognition for Natural Language. MIT Press, Cambridge (1980)"},{"key":"5_CR50","first-page":"313","volume":"19","author":"B Santorini","year":"1994","unstructured":"Santorini, B., Marcinkiewicz, M.: Building a large annotated corpus of english: The PennTreebank. Comput. Linguist. 19, 313\u2013330 (1994)","journal-title":"Comput. Linguist."},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Mihalcea, R., Moldovan, D.: A method for word sense disambiguation of unrestricted text. In: ACL, pp. 152\u2013158 (1999)","DOI":"10.3115\/1034678.1034709"},{"key":"5_CR52","unstructured":"Mikolov, Tomas, Yih, Wen-tau, Zweig, Geoffrey: Linguistic regularities in continuous space word representations.Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 746\u2013751. Atlanta, Georgia (2013)"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Modjeska, N., Markert, K. Nissim, M.: Using the web in machine learning for other-anaphora resolution. In: Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, 176\u2013183 ( 2003)","DOI":"10.3115\/1119355.1119378"},{"key":"5_CR54","unstructured":"Nakov, P.: Using the web as an implicit training set: Application to noun compound syntax and semantics. EECS Department, University of California, Berkeley, UCB\/EECS-2007-173 dissertation (2007)"},{"key":"5_CR55","unstructured":"Improved statistical machine translation using monolingual paraphrases. In: Proceedings of the European Conference on Artificial Intelligence, ECAI 2008, pp. 338\u2013342. Patras, Greece (2008a)"},{"key":"5_CR56","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/978-3-540-85776-1_10","volume-title":"Artificial Intelligence: Methodology, Systems, and Applications","author":"P Nakov","year":"2008","unstructured":"Nakov, P.: Noun compound interpretation using paraphrasing verbs: feasibility study. In: Dochev, D., Pistore, M., Traverso, P. (eds.) AIMSA 2008. LNCS (LNAI), vol. 5253, pp. 103\u2013117. Springer, Heidelberg (2008)"},{"key":"5_CR57","unstructured":"Paraphrasing verbs for noun compound interpretation. In: Proceedings of the LREC\u201908 Workshop: Towards a Shared Task for Multiword Expressions, MWE 2008, pp. 46\u201349. Marrakech, Morocco (2008c)"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"On the interpretation of noun compounds: Syntax, semantics, and entailment. Natural Lang. Eng. vol. 19, pp. 291\u2013330 (2013)","DOI":"10.1017\/S1351324913000065"},{"key":"5_CR59","unstructured":"Hearst, M.: Search engine statistics beyond the n-gram: Application to noun compound bracketing. In: Proceedings of CoNLL-2005, Ninth Conference on Computational Natural Language Learning (2005a)"},{"key":"5_CR60","unstructured":"Hearst, M.: A study of using search engine page hits as a proxy for n-gram frequencies. In: Proceedings of RANLP 2005, pp. 347\u2013353. Borovets, Bulgaria (2005)"},{"key":"5_CR61","doi-asserted-by":"crossref","unstructured":"Hearst, M.: Using the web as an implicit training set: application to structural ambiguity resolution. In: HLT 2005: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp. 835\u2013842. Association for Computational Linguistics, Morristown, NJ, USA (2005c)","DOI":"10.3115\/1220575.1220680"},{"key":"5_CR62","unstructured":"Hearst, M.: Solving relational similarity problems using the web as a corpus. In: Proceedings of the 46th Annual Meeting on Association for Computational Linguistics, ACL 2008, pp. 452\u2013460. Columbus, OH (2008)"},{"key":"5_CR63","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/11861461_25","volume-title":"Artificial Intelligence: Methodology, Systems, and Applications","author":"P Nakov","year":"2006","unstructured":"Nakov, P., Hearst, M.: Using verbs to characterize noun-noun relations. In: Euzenat, J., Domingue, J. (eds.) AIMSA 2006. LNCS (LNAI), vol. 4183, pp. 233\u2013244. Springer, Heidelberg (2006)"},{"key":"5_CR64","unstructured":"Kozareva, Z.: Combining relational and attributional similarity for semantic relation classification. In: Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2011, pp. 323\u2013330. Hissar, Bulgaria (2011)"},{"key":"5_CR65","unstructured":"Schwartz, A., Wolf, B., Hearst, M.: Scaling up BioNLP: application of a text annotation architecture to noun compound bracketing. In: Proceedings of SIG BioLINK (2005a)"},{"key":"5_CR66","unstructured":"Schwartz, A., Wolf, B., Hearst, M.: Proceedings of the ACL 2005 on interactive poster and demonstration sessions, pp. 65\u201368. Association for Computational Linguistics, Morristown, NJ, USA (2005b)"},{"key":"5_CR67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2483969.2483975","volume":"10","author":"PI Nakov","year":"2013","unstructured":"Nakov, P.I., Hearst, M.A.: Semantic interpretation of noun compounds using verbal and other paraphrases. ACM Trans. Speech Lang. Process. 10, 1\u201351 (2013)","journal-title":"ACM Trans. Speech Lang. Process."},{"key":"5_CR68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02148-0","volume-title":"Semantic Relations Between Nominals: Synthesis Lectures on Human Language Technologies","author":"V Nastase","year":"2013","unstructured":"Nastase, V., Nakov, P., S\u00e9aghdha, D.\u00d3., Szpakowicz, S.: Semantic Relations Between Nominals: Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers, San Rafael (2013)"},{"key":"5_CR69","doi-asserted-by":"crossref","unstructured":"Pantel, P., Lin, D.: An unsupervised approach to prepositional phrase attachment using contextually similar words. In: Proceedings of ACL (2000)","DOI":"10.3115\/1075218.1075232"},{"key":"5_CR70","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1108\/eb046814","volume":"14","author":"M Porter","year":"1980","unstructured":"Porter, M.: An algorithm for suffix stripping. Program 14, 130\u2013137 (1980)","journal-title":"Program"},{"key":"5_CR71","first-page":"331","volume":"19","author":"J Pustejovsky","year":"1993","unstructured":"Pustejovsky, J., Anick, P., Bergler, S.: Lexical semantic techniques for corpus analysis. Comput. Linguist. 19, 331\u2013358 (1993)","journal-title":"Comput. Linguist."},{"key":"5_CR72","doi-asserted-by":"crossref","unstructured":"Ratnaparkhi, A.: Statistical models for unsupervised prepositional phrase attachment. In: Proceedings of COLING-ACL vol. 2, pp. 1079\u20131085 (1998)","DOI":"10.3115\/980432.980746"},{"key":"5_CR73","doi-asserted-by":"crossref","unstructured":"Reynar, J., Roukos, S.: A maximum entropy model for prepositional phrase attachment. In: Proceedings of the ARPA Workshop on Human Language Technology, pp. 250\u2013255 (1994)","DOI":"10.3115\/1075812.1075868"},{"key":"5_CR74","unstructured":"Resnik, P.: Selection and information: a class-based approach to lexical relationships. University of Pennsylvania, UMI Order No. GAX94-13894 dissertation (1993)"},{"key":"5_CR75","doi-asserted-by":"crossref","unstructured":"Mining the web for bilingual text. In: Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics on Computational Linguistics, pp. 527\u2013534. Association for Computational Linguistics, Morristown, NJ, USA (1999a)","DOI":"10.3115\/1034678.1034757"},{"key":"5_CR76","doi-asserted-by":"crossref","unstructured":"Semantic similarity in a taxonomy: An information-based measure and its application to problems of ambiguity in natural language. In: JAIR 11, pp. 95\u2013130 (1999b)","DOI":"10.1613\/jair.514"},{"key":"5_CR77","doi-asserted-by":"crossref","unstructured":"Rigau, G., Magnini, B., Agirre, E., Carroll, J.: Meaning: A roadmap to knowledge technologies. In: Proceedings of COLING Workshop on A Roadmap for Computational Linguistics (2002)","DOI":"10.3115\/1118754.1118758"},{"key":"5_CR78","unstructured":"Rus, V., Moldovan, D., Bolohan, O.: Bracketing compound nouns for logic form derivation. In: Haller, S.M., Simmons, G. (eds.) FLAIRS Conference, pp. 198\u2013202. AAAI Press (2002)"},{"key":"5_CR79","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1162\/089120103322711613","volume":"29","author":"C Santamar\u00eda","year":"2003","unstructured":"Santamar\u00eda, C., Gonzalo, J., Verdejo, F.: Automatic association of web directories with word senses. Comput. Linguist. 29, 485\u2013502 (2003)","journal-title":"Comput. Linguist."},{"key":"5_CR80","unstructured":"Shinzato, K., Torisawa, K.: Acquiring hyponymy relations from web documents. In: Proceedings of HLT-NAACL, pp. 73\u201380 (2004)"},{"key":"5_CR81","unstructured":"Soricut, R., Brill, E.: Automatic question answering: Beyond the factoid. In: Proceedings of HLT-NAACL, pp. 57\u201364 (2004)"},{"key":"5_CR82","unstructured":"Stetina, J., Makoto.: Corpus based PP attachment ambiguity resolution with a semantic dictionary. In: Proceedings of WVLC, pp. 66\u201380 (1997)"},{"key":"5_CR83","doi-asserted-by":"crossref","unstructured":"Toutanova, K., Klein, D., Manning, C., Singer, Y.: Feature-rich part-of-speech tagging with a cyclic dependency network. In: Proceedings of HLT-NAACL 2003, pp. 252\u2013259 (2003)","DOI":"10.3115\/1073445.1073478"},{"key":"5_CR84","doi-asserted-by":"crossref","unstructured":"Toutanova, K., Manning, C.D., Andrew Y.Ng.: Learning random walk models for inducing word dependency distributions. In: Proceedings of ICML (2004)","DOI":"10.1145\/1015330.1015442"},{"key":"5_CR85","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/s10994-005-0913-1","volume":"60","author":"P Turney","year":"2005","unstructured":"Turney, P., Littman, M.: Corpus-based learning of analogies and semantic relations. Mach. Learn. J. 60, 251\u2013278 (2005)","journal-title":"Mach. Learn. J."},{"key":"5_CR86","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1162\/coli.2006.32.3.379","volume":"32","author":"PD Turney","year":"2006","unstructured":"Turney, P.D.: Similarity of semantic relations. Comput. Linguist. 32, 379\u2013416 (2006)","journal-title":"Comput. Linguist."},{"key":"5_CR87","unstructured":"V\u00e9ronis, J.: Web: Google adjusts its counts. Jean Veronis\u2019 blog: (2005a). http:\/\/aixtal.blogspot.com\/2005\/03\/web-google-adjusts-its-counts.html"},{"key":"5_CR88","unstructured":"Web: MSN cheating too? Jean Veronis\u2019 blog: (2005b). http:\/\/aixtal.blogspot.com\/2005\/02\/web-msn-cheating-too.html"},{"key":"5_CR89","unstructured":"Web: Yahoo doubles its counts! Jean Veronis\u2019 blog: (2005c). http:\/\/aixtal.blogspot.com\/2005\/03\/web-yahoo-doubles-its-counts.html"},{"key":"5_CR90","unstructured":"Volk, M.: Scaling up. using the www to resolve PP attachment ambiguities. In: Proceedings of Konvens-2000. Sprachkommunikation (2000)"},{"key":"5_CR91","unstructured":"Exploiting the WWW as a corpus to resolve PP attachment ambiguities. In: Proceedings of Corpus Linguistics (2001)"},{"key":"5_CR92","doi-asserted-by":"crossref","unstructured":"Wang, K., Thrasher, C., Paul Hsu, B.-J.: Web scale NLP: A case study on url word breaking. In: Proceedings of the 20th International Conference on World Wide Web, WWW 2011, pp. 357\u2013366. ACM, New York, NY, USA (2011)","DOI":"10.1145\/1963405.1963457"},{"key":"5_CR93","unstructured":"Warren, B.: Semantic patterns of noun-noun compounds. In: Gothenburg Studies in English 41, Goteburg, Acta Universtatis Gothoburgensis (1978)"},{"key":"5_CR94","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1162\/089120103322711596","volume":"29","author":"A Way","year":"2003","unstructured":"Way, A., Gough, N.: wEBMT: developing and validating an example-based machine translation system using the world wide web. Comput. Linguist. 29, 421\u2013457 (2003)","journal-title":"Comput. Linguist."},{"key":"5_CR95","unstructured":"Yang, Y., Pedersen, J.: A comparative study on feature selection in text categorization. In: Proceedings of ICML1997, pp. 412\u2013420 (1997)"},{"key":"5_CR96","unstructured":"Zahariev, M.: School of Computing Science, Simon Fraser University, USA dissertation (2004)"},{"key":"5_CR97","unstructured":"Zhu, X., Rosenfeld, R.: Improving trigram language modeling with the world wide web. In: Proceedings of ICASSP I, pp. 533\u2013536 (2001)"}],"container-title":["Communications in Computer and Information Science","Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-25485-2_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T18:34:49Z","timestamp":1748716489000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-25485-2_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319254845","9783319254852"],"references-count":97,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-25485-2_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"10 December 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RuSSIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russian Summer School in Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nizhniy Novgorod","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2014","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 August 2014","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2014","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"russir2014","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}