{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T11:38:24Z","timestamp":1767008304581,"version":"3.37.3"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,11,24]],"date-time":"2018-11-24T00:00:00Z","timestamp":1543017600000},"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":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10579-018-9438-7","type":"journal-article","created":{"date-parts":[[2018,11,24]],"date-time":"2018-11-24T15:14:24Z","timestamp":1543072464000},"page":"397-418","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A word sense disambiguation corpus for Urdu"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3779-2633","authenticated-orcid":false,"given":"Ali","family":"Saeed","sequence":"first","affiliation":[]},{"given":"Rao Muhammad Adeel","family":"Nawab","sequence":"additional","affiliation":[]},{"given":"Mark","family":"Stevenson","sequence":"additional","affiliation":[]},{"given":"Paul","family":"Rayson","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,11,24]]},"reference":[{"key":"9438_CR1","first-page":"1","volume":"1","author":"M Abid","year":"2017","unstructured":"Abid, M., Habib, A., Ashraf, J., & Shahid, A. (2017). Urdu word sense disambiguation using machine learning approach. Cluster Computing, 1, 1\u20138.","journal-title":"Cluster Computing"},{"volume-title":"Word sense disambiguation: Algorithms and applications (Vol. 33)","year":"2007","key":"9438_CR2","unstructured":"Agirre, E., & Edmonds, P. (Eds.). (2007). Word sense disambiguation: Algorithms and applications (Vol. 33). Berlin: Springer."},{"key":"9438_CR3","unstructured":"Ahmed, T., Urooj, S., Hussain, S., Mustafa, A., Parveen, R., Adeeba, F., Hautli, A., & Butt, M. (2014). The CLE Urdu POS tagset. In Poster presentation in language resources and evaluation conference (LERC 14)."},{"issue":"3","key":"9438_CR4","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/00031305.1992.10475879","volume":"46","author":"NS Altman","year":"1992","unstructured":"Altman, N. S. (1992). An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46(3), 175\u2013185.","journal-title":"The American Statistician"},{"issue":"20","key":"9438_CR5","first-page":"7609","volume":"9","author":"M Anand Kumar","year":"2014","unstructured":"Anand Kumar, M., Rajendran, S., & Soman, K. P. (2014). Tamil word sense disambiguation using support vector machines with rich features. International Journal of Applied Engineering Research, 9(20), 7609\u201320.","journal-title":"International Journal of Applied Engineering Research"},{"key":"9438_CR6","unstructured":"Appropriation, F. Y. A. F. Y. (1858). American Printing House for the Blind."},{"key":"9438_CR7","first-page":"305","volume":"12","author":"AI Arieff","year":"1912","unstructured":"Arieff, A. I. (1912). Veterans Administration Medical Center in San Francisco. San Jose Mercury, 12, 305.","journal-title":"San Jose Mercury"},{"issue":"5","key":"9438_CR8","first-page":"738","volume":"14","author":"SZ Arif","year":"2016","unstructured":"Arif, S. Z., Yaqoob, M. M., Rehman, A., & Jamil, F. (2016). Word sense disambiguation for Urdu text by machine learning. International Journal of Computer Science and Information Security, 14(5), 738.","journal-title":"International Journal of Computer Science and Information Security"},{"key":"9438_CR9","unstructured":"Baker, P., Hardie, A., McEnery, T., Cunningham, H., & Gaizauskas, R. J. (2002). EMILLE, A 67-million word corpus of Indic languages: Data collection, mark-up and harmonisation. In LREC."},{"key":"9438_CR10","unstructured":"Becker, D., Riaz, K., Bennett, B. H., Davis, E., & Panton, D. (2002). Named entity recognition in Urdu: A progress report. In International conference on internet computing (pp. 757\u2013761)."},{"key":"9438_CR11","unstructured":"Bhingardive, S., Singh, D., Rudramurthy, V., Redkar, H., & Bhattacharyya, P. (2015). Unsupervised most frequent sense detection using word embeddings. In Proceedings of the 2015 conference of the North American Chapter of the Association for Computational Linguistics: Human language technologies (pp. 1238\u20131243)."},{"key":"9438_CR12","volume-title":"Urdu Lughat","author":"UD Board","year":"2008","unstructured":"Board, U. D. (2008). Urdu Lughat. Karachi: Urdu Lughat Board."},{"key":"9438_CR13","unstructured":"Bond, F., Baldwin, T., Fothergill, R., & Uchimoto, K. (2012). Japanese SemCor: A sense-tagged corpus of Japanese. In Proceedings of the 6th global WordNet conference (GWC 2012) (pp. 56\u201363)."},{"key":"9438_CR14","doi-asserted-by":"crossref","unstructured":"Bruce, R., & Wiebe, J. (1994). Word-sense disambiguation using decomposable models. In Proceedings of the 32nd annual meeting on Association for Computational Linguistics (pp. 139\u2013146). Association for Computational Linguistics.","DOI":"10.3115\/981732.981752"},{"key":"9438_CR15","unstructured":"Cai, J., Lee, W. S., & Teh, Y. W. (2007). Improving word sense disambiguation using topic features. In Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning (EMNLP-CoNLL)."},{"key":"9438_CR16","unstructured":"Chklovski, T., Mihalcea, R., Pedersen, T., & Purandare, A. (2004). The Senseval-3 multilingual English\u2013Hindi lexical sample task. In Proceedings of SENSEVAL-3, the third international workshop on the evaluation of systems for the semantic analysis of text. Association for Computational Linguistics."},{"key":"9438_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-016-9482-x","volume":"47","author":"A Daud","year":"2016","unstructured":"Daud, A., Khan, W., & Che, D. (2016). Urdu language processing: A survey. Artificial Intelligence Review, 47, 1\u201333. https:\/\/doi.org\/10.1007\/s10462-016-9482-x .","journal-title":"Artificial Intelligence Review"},{"key":"9438_CR18","unstructured":"DiMarco, C., Covvey, H., Cowan, D., DiCiccio, V., Hovy, E., Lipa, J., & Mulholland, D. (2007). The development of a natural language generation system for personalized e-health information. In Medinfo 2007: Proceedings of the 12th world congress on health (medical) informatics; building sustainable health systems (p. 2339). IOS Press."},{"issue":"3","key":"9438_CR19","first-page":"5","volume":"7","author":"P Edmonds","year":"2002","unstructured":"Edmonds, P. (2002). SENSEVAL: The evaluation of word sense disambiguation systems. ELRA Newsletter, 7(3), 5\u201314.","journal-title":"ELRA Newsletter"},{"key":"9438_CR20","unstructured":"Edmonds, P., & Cotton, S. (2001). SENSEVAL-2: Overview. In The Proceedings of the Second International Workshop on Evaluating Word Sense Disambiguation Systems (pp. 1\u20135). Association for Computational Linguistics."},{"key":"9438_CR21","volume-title":"Brown corpus manual","author":"WN Francis","year":"1979","unstructured":"Francis, W. N., & Kucera, H. (1979). Brown corpus manual. Providence: Brown University."},{"issue":"1","key":"9438_CR22","doi-asserted-by":"publisher","first-page":"119","DOI":"10.3102\/0091732X023001119","volume":"23","author":"JP Gee","year":"1998","unstructured":"Gee, J. P., & Green, J. L. (1998). Chapter 4: Discourse analysis, learning, and social practice: A methodological study. Review of Research in Education, 23(1), 119\u2013169.","journal-title":"Review of Research in Education"},{"key":"9438_CR23","unstructured":"Huang, P. S., Damarla, T., & Hasegawa-Johnson, M. (2011). Multi-sensory features for personnel detection at border crossings. In 2011 Proceedings of the 14th international conference on information fusion (FUSION) (pp. 1\u20138). IEEE."},{"key":"9438_CR24","unstructured":"Hussain, S. (2008). Resources for Urdu language processing. In IJCNLP (pp. 99\u2013100)."},{"key":"9438_CR25","doi-asserted-by":"crossref","unstructured":"Hutchins, W. J. (1995). Machine translation: A brief history. In Concise history of the language sciences (pp. 431\u2013445). Elsevier.","DOI":"10.1016\/B978-0-08-042580-1.50066-0"},{"key":"9438_CR26","doi-asserted-by":"crossref","unstructured":"Iacobacci, I., Pilehvar, M. T., & Navigli, R. (2016). Embeddings for word sense disambiguation: An evaluation study. In Proceedings of the 54th annual meeting of the association for computational linguistics (Vol. 1, pp. 897\u2013907).","DOI":"10.18653\/v1\/P16-1085"},{"key":"9438_CR27","unstructured":"Ide, N. (1998). Corpus encoding standard: SGML guidelines for encoding linguistic corpora. In Proceedings of the first international language resources and evaluation conference (pp. 463\u2013470)."},{"key":"9438_CR28","unstructured":"Jawaid, B., Kamran, A., & Bojar, O. (2014). A tagged corpus and a tagger for Urdu. In LREC (pp. 2938\u20132943)."},{"key":"9438_CR29","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-1-4614-3223-4_2","volume-title":"Mining text data","author":"J Jiang","year":"2012","unstructured":"Jiang, J. (2012). Information extraction from text. In C. C. Aggarwal & C.-X. Zhai (Eds.), Mining text data (pp. 11\u201341). Boston: Springer."},{"issue":"6","key":"9438_CR30","first-page":"193","volume":"9","author":"SN Khan","year":"2018","unstructured":"Khan, S. N., Khan, K., Khan, A., Khan, A., Khan, A. U., & Ullah, B. (2018). Urdu word segmentation using machine learning approaches. International Journal of Advanced Computer Science and Applications, 9(6), 193\u2013200.","journal-title":"International Journal of Advanced Computer Science and Applications"},{"key":"9438_CR31","unstructured":"Kilgarriff, A. (2004). How dominant is the commonest sense of a word?. In International conference on text, speech and dialogue (pp. 103\u2013111). Berlin: Springer."},{"key":"9438_CR32","volume-title":"Building a semantic concordance of English. WordNet: An electronic lexical database and some applications","author":"S Landes","year":"1998","unstructured":"Landes, S., Leacock, C., & Tengi, R. (1998). Building a semantic concordance of English. WordNet: An electronic lexical database and some applications. Cambridge: MIT Press."},{"key":"9438_CR33","doi-asserted-by":"crossref","unstructured":"Leacock, C., Towell, G., & Voorhees, E. (1993). Corpus-based statistical sense resolution. In Proceedings of the workshop on human language technology (pp. 260\u2013265). Association for Computational Linguistics.","DOI":"10.3115\/1075671.1075730"},{"key":"9438_CR34","doi-asserted-by":"crossref","unstructured":"Lin, C. Y., & Hovy, E. (2000). The automated acquisition of topic signatures for text summarization. In Proceedings of the 18th conference on computational linguistics (Vol. 1, pp. 495\u2013501). Association for Computational Linguistics.","DOI":"10.3115\/990820.990892"},{"key":"9438_CR35","volume-title":"Data mining with decision trees: Theory and applications","author":"R Lior","year":"2014","unstructured":"Lior, R. (2014). Data mining with decision trees: Theory and applications (Vol. 81). Singapore: World Scientific."},{"key":"9438_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, Z., Chua, T.S., & Sun, M. (2015). Topical word embeddings. In AAAI (pp. 2418\u20132424).","DOI":"10.1609\/aaai.v29i1.9522"},{"issue":"4","key":"9438_CR37","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/BF02478259","volume":"5","author":"WS McCulloch","year":"1943","unstructured":"McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics, 5(4), 115\u2013133.","journal-title":"The Bulletin of Mathematical Biophysics"},{"issue":"3","key":"9438_CR38","first-page":"22","volume":"13","author":"A McEnery","year":"2000","unstructured":"McEnery, A., Baker, P., Gaizauskas, R., & Cunningham, H. (2000). EMILLE: Building a corpus of South Asian languages. VIVEK-BOMBAY, 13(3), 22\u201328.","journal-title":"VIVEK-BOMBAY"},{"key":"9438_CR39","volume-title":"The new Oxford American dictionary","author":"E McKean","year":"2005","unstructured":"McKean, E. (2005). The new Oxford American dictionary (Vol. 2). New York: Oxford University Press."},{"key":"9438_CR40","unstructured":"Mihalcea, R., Chklovski, T., & Kilgarriff, A. (2004). The Senseval-3 English lexical sample task. In Proceedings of SENSEVAL-3, the third international workshop on the evaluation of systems for the semantic analysis of text."},{"key":"9438_CR41","unstructured":"Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781."},{"key":"9438_CR42","first-page":"126","volume":"12","author":"N Mishra","year":"2012","unstructured":"Mishra, N., & Siddiqui, T. J. (2012). An investigation to semi supervised approach for HINDI word sense disambiguation. Trends in Innovative Computing 2012-Intelligent Systems Design, 12, 126\u2013130.","journal-title":"Trends in Innovative Computing 2012-Intelligent Systems Design"},{"key":"9438_CR43","unstructured":"Narayan, D., Chakrabarti, D., Pande, P., & Bhattacharyya, P. (2002). An experience in building the indo WordNet\u2014A WordNet for Hindi. In First international conference on global WordNet, Mysore, India."},{"key":"9438_CR44","volume-title":"Supervised word sense disambiguation for Urdu using Bayesian classification","author":"A Naseer","year":"2009","unstructured":"Naseer, A., & Hussain, S. (2009). Supervised word sense disambiguation for Urdu using Bayesian classification. Lahore: Center for Research in Urdu Language Processing."},{"issue":"2","key":"9438_CR45","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1459352.1459355","volume":"41","author":"R Navigli","year":"2009","unstructured":"Navigli, R. (2009). Word sense disambiguation: A survey. ACM Computing Surveys (CSUR), 41(2), 10.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"9438_CR46","unstructured":"Ng, H. T., Lim, C. Y., & Foo, S. K. (1999). A case study on inter-annotator agreement for word sense disambiguation. SIGLEX99: Standardizing Lexical Resources, W99-05, W99-0502."},{"key":"9438_CR47","unstructured":"Palmer, M., Fellbaum, C., Cotton, S., Delfs, L., & Dang, H. T. (2001). English tasks: All-words and verb lexical sample. In The proceedings of the second international workshop on evaluating word sense disambiguation systems (pp. 21\u201324). Association for Computational Linguistics."},{"key":"9438_CR48","unstructured":"Passonneau, R. J., Baker, C., Fellbaum, C., & Ide, N. (2012). The MASC word sense sentence corpus. In Proceedings of LREC."},{"key":"9438_CR49","unstructured":"Pedersen, T. (2000). A simple approach to building ensembles of Naive Bayesian classifiers for word sense disambiguation. In Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference (pp. 63\u201369). Association for Computational Linguistics."},{"key":"9438_CR50","first-page":"1","volume":"5","author":"BD Prasad","year":"2008","unstructured":"Prasad, B. D. (2008). Content analysis. Research Methods for Social Work, 5, 1\u201320.","journal-title":"Research Methods for Social Work"},{"key":"9438_CR51","unstructured":"Rahman, T. (2004). Language policy and localization in Pakistan: Proposal for a paradigmatic shift. In SCALLA conference on computational linguistics (Vol. 99, p. 100)."},{"key":"9438_CR52","unstructured":"Riaz, K. (2010). Rule-based named entity recognition in Urdu. In Proceedings of the 2010 named entities workshop (pp. 126\u2013135). Association for Computational Linguistics."},{"key":"9438_CR53","unstructured":"Rong, X. (2014). Word2vec parameter learning explained. arXiv preprint arXiv:1411.2738."},{"key":"9438_CR54","volume-title":"Introduction to information retrieval","author":"H Sch\u00fctze","year":"2008","unstructured":"Sch\u00fctze, H., Manning, C. D., & Raghavan, P. (2008). Introduction to information retrieval (Vol. 39). Cambridge: Cambridge University Press."},{"issue":"3","key":"9438_CR55","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1007\/s10579-016-9367-2","volume":"51","author":"M Sharjeel","year":"2017","unstructured":"Sharjeel, M., Nawab, R. M. A., & Rayson, P. (2017). COUNTER: Corpus of Urdu news text reuse. Language Resources and Evaluation, 51(3), 777\u2013803.","journal-title":"Language Resources and Evaluation"},{"key":"9438_CR56","unstructured":"Singh, U., Goyal, V., & Lehal, G. S. (2012). Named entity recognition system for Urdu. In Proceedings of COLING 2012 (pp. 2507\u20132518)."},{"key":"9438_CR57","unstructured":"Sinha, M., Kumar, M., Pande, P., Kashyap, L., & Bhattacharyya, P. (2004). Hindi word sense disambiguation. In International symposium on machine translation, natural language processing and translation support systems, Delhi, India."},{"issue":"4","key":"9438_CR58","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","volume":"45","author":"M Sokolova","year":"2009","unstructured":"Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427\u2013437.","journal-title":"Information Processing & Management"},{"key":"9438_CR59","first-page":"1","volume":"6","author":"T Sreeganesh","year":"2006","unstructured":"Sreeganesh, T. (2006). Telugu parts of speech tagging in WSD. Language of India, 6, 1.","journal-title":"Language of India"},{"key":"9438_CR60","doi-asserted-by":"crossref","unstructured":"Taghipour, K., & Ng, H. T. (2015). One million sense-tagged instances for word sense disambiguation and induction. In Proceedings of the nineteenth conference on computational natural language learning (pp. 338\u2013344).","DOI":"10.18653\/v1\/K15-1037"},{"key":"9438_CR61","unstructured":"Urooj, S., Shams, S., Hussain, S., & Adeeba, F. (2014). Sense tagged CLE Urdu digest corpus. In Proceedings of conference on language and technology, Karachi."},{"key":"9438_CR62","unstructured":"Vossen, P., Izquierdo, R., & G\u00f6r\u00f6g, A. (2013). DutchSemCor: In quest of the ideal sense-tagged corpus. In Proceedings of the international conference recent advances in natural language processing RANLP 2013 (pp. 710\u2013718)."},{"key":"9438_CR63","unstructured":"Zafar, A., Mahmood, A., Abdullah, F., Zahid, S., Hussain, S., & Mustafa, A. (2012). Developing Urdu WordNet using the merge approach. In Proceedings of the conference on language and technology (pp. 55\u201359)."}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-018-9438-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-018-9438-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-018-9438-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T18:49:41Z","timestamp":1720810181000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-018-9438-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,24]]},"references-count":63,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["9438"],"URL":"https:\/\/doi.org\/10.1007\/s10579-018-9438-7","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"type":"print","value":"1574-020X"},{"type":"electronic","value":"1574-0218"}],"subject":[],"published":{"date-parts":[[2018,11,24]]},"assertion":[{"value":"24 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}