{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T13:11:16Z","timestamp":1762089076113,"version":"build-2065373602"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T00:00:00Z","timestamp":1688515200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T00:00:00Z","timestamp":1688515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-023-01885-z","type":"journal-article","created":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T16:23:58Z","timestamp":1688574238000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Semi-automatic Annotation for Mentions in Hindi Text"],"prefix":"10.1007","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9492-7653","authenticated-orcid":false,"given":"Kusum","family":"Lata","sequence":"first","affiliation":[]},{"given":"Pardeep","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Kamlesh","family":"Dutta","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,5]]},"reference":[{"issue":"4","key":"1885_CR1","doi-asserted-by":"publisher","first-page":"161","DOI":"10.3390\/ijgi8040161","volume":"8","author":"M Karimzadeh","year":"2019","unstructured":"Karimzadeh M, MacEachren AM. GeoAnnotator: a collaborative semi-automatic platform for constructing geo-annotated text corpora. ISPRS Int J Geo-Inf. 2019;8(4):161.","journal-title":"ISPRS Int J Geo-Inf"},{"issue":"40","key":"1885_CR2","doi-asserted-by":"publisher","first-page":"4216","DOI":"10.17485\/IJST\/v13i40.1451","volume":"13","author":"N Garg","year":"2020","unstructured":"Garg N, Sharma K. Annotated corpus creation for sentiment analysis in code-mixed Hindi-English (Hinglish) social network data. Indian J Sci Technol. 2020;13(40):4216\u201324.","journal-title":"Indian J Sci Technol"},{"key":"1885_CR3","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1007\/978-981-16-9605-3_53","volume-title":"Evolutionary computing and mobile sustainable networks: proceedings of ICECMSN 2021","author":"AK ShetTilve","year":"2022","unstructured":"ShetTilve AK, Patkar G, Fernandes L, Prabhudesai P, Sawant MP, Maurya S. Corpus creation and annotation framework for sentiment analysis of Hindi news articles. In: Evolutionary computing and mobile sustainable networks: proceedings of ICECMSN 2021. Springer; 2022. p. 773\u201384."},{"unstructured":"Venugopal G, Pramod D, Shekhar R. CWID-hi: a dataset for complex word identification in Hindi text. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, 2022, pp. 5627\u201336.","key":"1885_CR4"},{"unstructured":"Sujoy S, Krishna A, Goyal P. Pre-annotation based approach for development of a Sanskrit named entity recognition dataset. In: Proceedings of the Computational Sanskrit and Digital Humanities: Selected Papers Presented at the 18th World Sanskrit Conference, 2023, pp. 59\u201370.","key":"1885_CR5"},{"key":"1885_CR6","first-page":"1050","volume":"2","author":"JF McCarthy","year":"1995","unstructured":"McCarthy JF, Lehnert WG. Using decision trees for conference resolution. Proc Int Jt Conf Artif Intell. 1995;2:1050\u20135.","journal-title":"Proc Int Jt Conf Artif Intell"},{"issue":"4","key":"1885_CR7","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1162\/089120101753342653","volume":"27","author":"WM Soon","year":"2001","unstructured":"Soon WM, Ng HT, Lim DC. A machine learning approach to coreference resolution of noun phrases. Comput Linguist. 2001;27(4):521\u201344.","journal-title":"Comput Linguist"},{"issue":"1","key":"1885_CR8","first-page":"20502","volume":"2","author":"Ace Phase 2 Program Committee and Others","year":"2003","unstructured":"Ace Phase 2 Program Committee and Others. Entity detection and tracking\u2014phase 1. EDT Metonymy Annot Guidel Vers. 2003;2(1):20502.","journal-title":"EDT Metonymy Annot Guidel Vers"},{"key":"1885_CR9","doi-asserted-by":"publisher","DOI":"10.21236\/ADA460245","volume-title":"A statistical model for multilingual entity detection and tracking","author":"R Florian","year":"2004","unstructured":"Florian R, Hassan H, Ittycheriah A, Jing H, Kambhatla N, Luo X, Nicolov H, Roukos S. A statistical model for multilingual entity detection and tracking. IBM Thomas J Watson Research Center Yorktown Heights; 2004."},{"doi-asserted-by":"crossref","unstructured":"Mintz M, Bills S, Snow R, Jurafsky D. Distant supervision for relation extraction without labeled data. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, 2009, pp. 1003\u201311.","key":"1885_CR10","DOI":"10.3115\/1690219.1690287"},{"unstructured":"Guo S, Chang MW, Kiciman E. To link or not to link? a study on end-to-end tweet entity linking. In: Proceedings of the 2013 conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2013, pp. 1020\u201330.","key":"1885_CR11"},{"issue":"4","key":"1885_CR12","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1162\/COLI_a_00152","volume":"39","author":"H Lee","year":"2013","unstructured":"Lee H, Chang A, Peirsman Y, Chambers N, Surdeanu M, Jurafsky D. Deterministic coreference resolution based on entity-centric, precision-ranked rules. Comput Linguist. 2013;39(4):885\u2013916.","journal-title":"Comput Linguist"},{"key":"1885_CR13","volume-title":"Syntactic restrictions and discourse functions of word order in standard Hindi","author":"V Gambhir","year":"1981","unstructured":"Gambhir V. Syntactic restrictions and discourse functions of word order in standard Hindi. Doctoral dissertation, University of Pennsylvania; 1981."},{"key":"1885_CR14","first-page":"17","volume":"55","author":"K Sourabh","year":"2012","unstructured":"Sourabh K, Mansotra V. Query optimization: a solution for low recall problem in Hindi language information retrieval. Int J Comput Appl. 2012;55:17.","journal-title":"Int J Comput Appl"},{"issue":"4","key":"1885_CR15","first-page":"219","volume":"59","author":"A Tripathi","year":"2013","unstructured":"Tripathi A. Problems and prospects of Hindi language search and text processing. Ann Libr Inf Stud (ALIS). 2013;59(4):219\u201322.","journal-title":"Ann Libr Inf Stud (ALIS)"},{"key":"1885_CR16","volume-title":"Argument structure in Hindi","author":"T Mohanan","year":"1994","unstructured":"Mohanan T. Argument structure in Hindi. Center for the Study of Language (CSLI); 1994."},{"key":"1885_CR17","volume-title":"Indian language part-of-speech tagset: Hindi","author":"K Bali","year":"2010","unstructured":"Bali K, Choudhury M, Biswas P, Jha GN, Choudhary N, Sharma M. Indian language part-of-speech tagset: Hindi. Linguistic Data Consortium; 2010."},{"unstructured":"Kunchukuttan A, Mehta P, Bhattacharyya P. The IIT Bombay English-Hindi parallel corpus. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018.","key":"1885_CR18"},{"unstructured":"Dakwale P, Sharma H, Sharma DM. Anaphora annotation in Hindi dependency treebank. In: Proceedings of the 26th Pacific Asia Conference on Language, Information, and Computation, 2012, pp. 391\u2013400.","key":"1885_CR19"},{"unstructured":"Venkataramana RM, Bhattacharjee P, Sharnagat R, Khatri J, Kanojia D, Bhattacharyya P. HiNER: a large Hindi Named Entity Recognition Dataset. In: International Conference on Language Resources and Evaluation, 2022.","key":"1885_CR20"},{"unstructured":"Chinchor NA, Sundheim B. Message understanding conference (MUC) tests of discourse processing. In: Proceedings of AAAI Spring Symposium on Empirical Methods in Discourse Interpretation and Generation, 1995, pp. 21\u20136.","key":"1885_CR21"},{"unstructured":"Hirschman L, Chinchor N. Appendix f: Muc-7 conference task definition (version 3.0). In: Seventh Message Understanding Conference (MUC-7): Proceedings of a Conference Held in Fairfax, Virginia, 1998.","key":"1885_CR22"},{"issue":"1","key":"1885_CR23","first-page":"837","volume":"2","author":"GR Doddington","year":"2004","unstructured":"Doddington GR, Mitchell A, Przybocki MA, Ramshaw LA, Strassel SM, Weischedel RM. The automatic content extraction (ace) program-tasks, data, and evaluation. LREC. 2004;2(1):837\u201340.","journal-title":"LREC"},{"unstructured":"Pradhan S, Moschitti A, Xue N, Uryupina O, Zhang Y. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In: Joint Conference on EMNLP and CoNLL-Shared Task 2012, 2012, pp. 1\u201340.","key":"1885_CR24"},{"unstructured":"Poesio M, Artstein R. Anaphoric Annotation in the ARRAU Corpus. In: Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), 2008.","key":"1885_CR25"},{"unstructured":"Ghaddar A, Langlais P. Wikicoref: An english coreference-annotated corpus of wikipedia articles. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (L,REC'16); 2016, pp. 136\u201342.","key":"1885_CR26"},{"issue":"3","key":"1885_CR27","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s10579-016-9343-x","volume":"51","author":"A Zeldes","year":"2017","unstructured":"Zeldes A. The GUM corpus: Creating multilayer resources in the classroom. Lang Resour Eval. 2017;51(3):581\u2013612.","journal-title":"Lang Resour Eval"},{"doi-asserted-by":"crossref","unstructured":"Chen H, Fan Z, Lu H, Yuille A, Rong S. PreCo: A large-scale dataset in preschool vocabulary for coreference resolution. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, pp. 172\u201381.","key":"1885_CR28","DOI":"10.18653\/v1\/D18-1016"},{"key":"1885_CR29","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1162\/tacl_a_00240","volume":"6","author":"K Webster","year":"2018","unstructured":"Webster K, Recasens M, Axelrod V, Baldridge J. Mind the GAP: a balanced corpus of gendered ambiguous pronouns. Trans Assoc Comput Linguist. 2018;6:605\u201317.","journal-title":"Trans Assoc Comput Linguist"},{"key":"1885_CR30","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/978-3-662-47909-4_4","volume-title":"Anaphora resolution","author":"M Poesio","year":"2016","unstructured":"Poesio M, Pradhan S, Recasens M, Rodriguez K, Versley Y. Annotated corpora and annotation tools. In: Anaphora resolution. Springer; 2016. p. 97\u2013140."},{"key":"1885_CR31","volume-title":"A corpus-based account of anaphor resolution in Hindi. Master\u2019s thesis","author":"S Sinha","year":"2016","unstructured":"Sinha S. A corpus-based account of anaphor resolution in Hindi. Master\u2019s thesis. University of Lancaster; 2016."},{"unstructured":"Sobha L, Bandyopadhyay S, Ram RVS, Akilandeswari A. NLP tool contest@ ICON2011 on anaphora resolution in indian languages. In: Proceedings of ICON, 2011.","key":"1885_CR32"},{"unstructured":"Mujadia V, Gupta P, Sharma DM. Coreference annotation scheme and relation types for Hindi. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), 2016, pp. 161\u20138.","key":"1885_CR33"},{"key":"1885_CR34","first-page":"1","volume-title":"Ssf: Shakti standard format guide","author":"A Bharati","year":"2007","unstructured":"Bharati A, Sangal R, Sharma DM. Ssf: Shakti standard format guide. Language Technologies Research Centre, International Institute of Information Technology; 2007. p. 1\u201325."},{"unstructured":"Singh S, Patel K, Bhattacharyya P. Attention based anaphora resolution for code-mixed social media text for Hindi language. In: FIRE (Working Notes), 2020, pp. 780\u20137.","key":"1885_CR35"},{"doi-asserted-by":"crossref","unstructured":"Poesio M, Grishina Y, Kolhatkar V, Moosavi NS, Roesiger I, Roussel A, Simonjetz F, Uma A, Uryupina O, Yu J, Zinsmeister H. Anaphora resolution with the ARRAU corpus. In: Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference, 2018, pp. 11\u201322.","key":"1885_CR36","DOI":"10.18653\/v1\/W18-0702"},{"key":"1885_CR37","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-94-017-2390-9_10","volume-title":"Natural language processing using very large corpora","author":"LA Ramshaw","year":"1999","unstructured":"Ramshaw LA, Marcus MP. Text chunking using transformation-based learning. In: Natural language processing using very large corpora. Springer; 1999. p. 157\u201376."},{"key":"1885_CR38","volume-title":"Capturing and resolving entities and their mentions in discourse","author":"MV Vasantlal","year":"2017","unstructured":"Vasantlal MV. Capturing and resolving entities and their mentions in discourse. Doctoral Dissertation, Doctoral Dissertation, International Institute of Information Technology Hyderabad; 2017."},{"unstructured":"Begum R, Husain S, Dhwaj A, Sharma DM, Bai L, Sangal R. Dependency annotation scheme for Indian languages. In: Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-II, 2008.","key":"1885_CR39"},{"key":"1885_CR40","first-page":"298","volume":"245","author":"M Boguslav","year":"2017","unstructured":"Boguslav M, Cohen KB. Inter-nnotator agreement and the upper limit on machine performance: evidence from biomedical natural language processing. Stud Health Technol Inform. 2017;245:298\u2013302.","journal-title":"Stud Health Technol Inform"},{"key":"1885_CR41","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1086\/266577","volume":"1","author":"WA Scott","year":"1955","unstructured":"Scott WA. Reliability of content analysis: The case of nominal scale coding. Public Opin Q. 1955;1:321\u20135.","journal-title":"Public Opin Q"},{"issue":"1","key":"1885_CR42","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen J. A coefficient of agreement for nominal scales. Educ Psychol Meas. 1960;20(1):37\u201346.","journal-title":"Educ Psychol Meas"},{"issue":"2","key":"1885_CR43","first-page":"183","volume":"24","author":"M Poesio","year":"1998","unstructured":"Poesio M. A corpus-based investigation of definite description use. Comput Linguist. 1998;24(2):183\u2013216.","journal-title":"Comput Linguist"},{"key":"1885_CR44","volume-title":"Content analysis: an introduction to its methodology","author":"K Krippendorff","year":"2018","unstructured":"Krippendorff K. Content analysis: an introduction to its methodology. Sage publications; 2018."},{"issue":"4","key":"1885_CR45","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1162\/coli.07-034-R2","volume":"34","author":"R Artstein","year":"2008","unstructured":"Artstein R, Poesio M. Inter-coder agreement for computational linguistics. Comput Linguist. 2008;34(4):555\u201396.","journal-title":"Comput Linguist"},{"unstructured":"Brandsen A, Verberne S, Lambers K, Wansleeben M, Calzolari N, B\u00e9chet F, Blache P, Choukri K, Cieri C, Declerck T, Goggi S. Creating a dataset for named entity recognition in the archaeology domain. In: Conference Proceedings LREC. The European Language Resources Association, 2020 pp. 4573\u20137.","key":"1885_CR46"},{"issue":"3","key":"1885_CR47","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/j.eij.2020.10.004","volume":"22","author":"N Alshammari","year":"2021","unstructured":"Alshammari N, Alanazi S. The impact of using different annotation schemes on named entity recognition. Egypt Inform J. 2021;22(3):295\u2013302.","journal-title":"Egypt Inform J"},{"unstructured":"Nandigam P, Appidi A, Shrivastava M. Named entity recognition for code-mixed Kannada\u2013English social media data. In: Proceedings of the 19th International Conference on Natural Language Processing (ICON), 2022, pp. 43\u20139.","key":"1885_CR48"},{"key":"1885_CR49","doi-asserted-by":"publisher","first-page":"9816","DOI":"10.1007\/s10489-021-02878-2","volume":"52","author":"K Lata","year":"2022","unstructured":"Lata K, Singh P, Dutta K. Mention detection in coreference resolution: survey. Appl Intell. 2022;52:9816\u201360.","journal-title":"Appl Intell"},{"unstructured":"Chinchor N. Appendix b: Muc-7 test scores introduction. In:\u00a0Seventh Message Understanding Conference (MUC-7): Proceedings of a Conference Held in Fairfax, Virginia, 1998.","key":"1885_CR50"},{"issue":"4","key":"1885_CR51","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1108\/eb026584","volume":"30","author":"CJ Van Rijsbergen","year":"1974","unstructured":"Van Rijsbergen CJ. Foundation of evaluation. J Doc. 1974;30(4):365\u201373.","journal-title":"J Doc"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-01885-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-023-01885-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-01885-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T16:51:14Z","timestamp":1688575874000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-023-01885-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,5]]},"references-count":51,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["1885"],"URL":"https:\/\/doi.org\/10.1007\/s42979-023-01885-z","relation":{},"ISSN":["2661-8907"],"issn-type":[{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2023,7,5]]},"assertion":[{"value":"22 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"The authors declare that the submitted work is original research that has not been published previously, and not under consideration for publication elsewhere, in whole or in part. All the authors listed have approved the manuscript that is enclosed.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"515"}}