{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T22:05:33Z","timestamp":1784066733480,"version":"3.55.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2015,5,28]],"date-time":"2015-05-28T00:00:00Z","timestamp":1432771200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2015,5,28]],"date-time":"2015-05-28T00:00:00Z","timestamp":1432771200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-08-C-0004"],"award-info":[{"award-number":["HR0011-08-C-0004"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2015,9]]},"DOI":"10.1007\/s10032-015-0247-x","type":"journal-article","created":{"date-parts":[[2015,5,27]],"date-time":"2015-05-27T08:21:04Z","timestamp":1432714864000},"page":"235-247","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Integrating natural language processing with image document analysis: what we learned from two real-world applications"],"prefix":"10.1007","volume":"18","author":[{"given":"Jinying","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaigu","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Premkumar","family":"Natarajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,5,28]]},"reference":[{"key":"247_CR1","doi-asserted-by":"crossref","unstructured":"Al-Subaihin, A.A., Al-Khalifa, H.S., Al-Salman, A.S.: Sentence boundary detection in colloquial arabic text: a preliminary result. In: Proceedings of 2011 International Conference on Asian Language Processing, pp. 30\u201332 (2011)","DOI":"10.1109\/IALP.2011.38"},{"key":"247_CR2","unstructured":"Alotaiby, F., Alkharashi, I., Foda, S.: Processing large arabic text corpora: Preliminary analysis and results. In: Proceedings of the Second International Conference on Arabic Language Resources and Tools, pp. 78\u201382 (2009)"},{"issue":"2","key":"247_CR3","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.specom.2003.07.003","volume":"42","author":"F B\u00e9chet","year":"2004","unstructured":"B\u00e9chet, F., Gorin, A.L., Wright, J.H., Hakkani T\u00fcr, D.: Detecting and extracting named entities from spontaneous speech in a mixed-initiative spoken dialogue context: how may i help you? Speech Commun. 42(2), 207\u2013225 (2004)","journal-title":"Speech Commun."},{"key":"247_CR4","doi-asserted-by":"crossref","unstructured":"Bhardwaj, A., Setlur, S., Govindaraju, V.: Keyword spotting techniques for sanskrit documents. In: Sanskrit Computational Linguistics, pp. 403\u2013416. Springer, Berlin (2009)","DOI":"10.1007\/978-3-642-00155-0_22"},{"key":"247_CR5","unstructured":"Cao, H., Chen, J., Devlin, J., Prasad, R., Natarajan, P.: Document recognition and translation system for unconstrained arabic documents. In: Proceedings of Pattern Recognition (ICPR), 21st International Conference on IEEE, pp. 318\u2013321 (2012)"},{"key":"247_CR6","doi-asserted-by":"crossref","unstructured":"Cao, H., Natarajan, P., Peng, X., Belanger, K.S.D., Li, N.: Progress in the raytheon bbn arabic online handwriting recognition system. In: Proceedings of Frontiers in Handwriting Recognition (ICFHR), 14th International Conference on IEEE, pp. 555\u2013560 (2014)","DOI":"10.1109\/ICFHR.2014.99"},{"key":"247_CR7","doi-asserted-by":"crossref","unstructured":"Chan, J., Ziftci, C., Forsyth, D.: Searching online arabic documents. In: Proceedings of Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on IEEE, vol. 2, pp. 1455\u20131462 (2006)","DOI":"10.1109\/CVPR.2006.269"},{"key":"247_CR8","doi-asserted-by":"crossref","unstructured":"Chen, J., Cao, H., Prasad, R., Bhardwaj, A., Natarajan, P.: Gabor features for online arabic handwriting recognition. In: Proceedings of the 9th IAPR International Workshop on Document Analysis Systems, pp. 53\u201358 (2010)","DOI":"10.1145\/1815330.1815337"},{"key":"247_CR9","doi-asserted-by":"crossref","unstructured":"Chen, J., Cao, H., Wu, Y., Natarajan, P.: Confusion network based recurrent neural network language modeling for chinese ocr error detection. In: Proceedings of ICPR, pp. 1266\u20131271 (2014)","DOI":"10.1109\/ICPR.2014.227"},{"key":"247_CR10","doi-asserted-by":"crossref","unstructured":"Chen, J., Prasad, R., Cao, H., Natarajan, P.: Detecting oov names in arabic handwritten data. In: Proceedings of Document Analysis and Recognition (ICDAR), 12th International Conference on IEEE, pp. 994\u2013998 (2013)","DOI":"10.1109\/ICDAR.2013.200"},{"key":"247_CR11","doi-asserted-by":"crossref","unstructured":"Chen, W., Ananthakrishnan, S., Kumar, R., Prasad, R., Natarajan, P.: Asr error detection in a conversational spoken language translation system. In: Proceedings of Acoustics, Speech and Signal Processing (ICASSP), IEEE International Conference on IEEE, pp. 7418\u20137422 (2013)","DOI":"10.1109\/ICASSP.2013.6639104"},{"key":"247_CR12","doi-asserted-by":"crossref","unstructured":"Chiang, D., Knight, K., Wang, W.: 11,001 new features for statistical machine translation. In: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 218\u2013226 (2009)","DOI":"10.3115\/1620754.1620786"},{"key":"247_CR13","doi-asserted-by":"crossref","unstructured":"Ding, W., Suen, C.Y., Krzyzak, A.: A new courtesy amount recognition module of a check reading system. In: Proceedings of ICPR, pp. 1\u20134 (2008)","DOI":"10.1109\/ICPR.2008.4761532"},{"key":"247_CR14","unstructured":"Farooq, F., Al-Onaizan, Y.: Effect of degraded input on statistical machine translation. In: 2005 Symposium on Document Image Understanding Technology, pp. 103\u2013109 (2005)"},{"key":"247_CR15","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"M Gales","year":"1998","unstructured":"Gales, M.: Maximum likelihood linear transformations for hmm-based speech recognition. Comput. Speech Lang. 12, 75\u201398 (1998)","journal-title":"Comput. Speech Lang."},{"key":"247_CR16","first-page":"79","volume":"1994","author":"G Grefenstette","year":"1994","unstructured":"Grefenstette, G., Tapanainen, P.: What is a word, what is a sentence? Problems of tokenization. COMPLEX 1994, 79\u201387 (1994)","journal-title":"COMPLEX"},{"key":"247_CR17","doi-asserted-by":"crossref","unstructured":"Huang, L., Yin, F., Chen, Q.H., Liu, C.L.: Keyword spotting in online chinese handwritten documents using a statistical model. In: Proceedings of ICDAR, pp. 78\u201382 (2011)","DOI":"10.1109\/ICDAR.2011.25"},{"key":"247_CR18","unstructured":"Khalifa, I., Feki, Z.A., Farawila, A.: Arabic discourse segmentation based on rhetorical methods. Int. J. Electr. Comput. Sci. 11(1), 10\u201315 (2011)"},{"issue":"4","key":"247_CR19","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1109\/34.588017","volume":"19","author":"G Kim","year":"1997","unstructured":"Kim, G., Govindaraju, V.: A lexicon driven approach to handwritten word recognition for real-time applications. IEEE Trans. Pattern Anal. Mach. Intell. 19(4), 366\u2013379 (1997)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"247_CR20","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1162\/coli.2006.32.4.485","volume":"32","author":"T Kiss","year":"2006","unstructured":"Kiss, T., Strunk, J.: Unsupervised multilingual sentence boundary detection. Comput. Linguist. 32(4), 485\u2013525 (2006)","journal-title":"Comput. Linguist."},{"key":"247_CR21","unstructured":"Kubala, F., Schwartz, R., Stone, R., Weischedel, R.: Named entity extraction from speech. In: Proceedings of DARPA Broadcast News Transcription and Understanding Workshop, pp. 287\u2013292 (1998)"},{"key":"247_CR22","unstructured":"Lafferty, J.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of International Conference on Machine Learning, pp. 282\u2013289 (2001)"},{"key":"247_CR23","doi-asserted-by":"crossref","unstructured":"Lin, H., Bilmes, J., Vergyri, D., Kirchhoff, K.: Oov detection by joint word\/phone lattice alignment. In: Proceedings of Automatic Speech Recognition and Understanding (ASRU), IEEE Workshop on IEEE, pp. 478\u2013483 (2007)","DOI":"10.1109\/ASRU.2007.4430159"},{"key":"247_CR24","doi-asserted-by":"crossref","unstructured":"Liu, C.L., Koga, M., Fujisawa, H.: Gabor feature extraction for character recognition: comparison with gradient feature. In: Proceedings of Document Analysis and Recognition, 8th International Conference on IEEE, pp. 121\u2013125 (2005)","DOI":"10.1109\/ICDAR.2005.119"},{"issue":"1\u20133","key":"247_CR25","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/BF01589116","volume":"45","author":"DC Liu","year":"1989","unstructured":"Liu, D.C., Nocedal, J.: On the limited memory bfgs method for large scale optimization. Math. Program. 45(1\u20133), 503\u2013528 (1989)","journal-title":"Math. Program."},{"key":"247_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Shriberg, E.: Comparing evaluation metrics for sentence boundary detection. In: Proceedings of ICASSP, pp. 451\u2013458 (2007)","DOI":"10.1109\/ICASSP.2007.367194"},{"issue":"5","key":"247_CR27","doi-asserted-by":"publisher","first-page":"1526","DOI":"10.1109\/TASL.2006.878255","volume":"14","author":"Y Liu","year":"2006","unstructured":"Liu, Y., Shriberg, E., Stolcke, A., Hillard, D., Ostendorf, M., Harper, M.P.: Enriching speech recognition with automatic detection of sentence boundaries and disfluencies. IEEE Trans. Audio, Speech Lang. Process. 14(5), 1526\u20131540 (2006)","journal-title":"IEEE Trans. Audio, Speech Lang. Process."},{"issue":"4","key":"247_CR28","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1006\/csla.2000.0152","volume":"14","author":"L Mangu","year":"2000","unstructured":"Mangu, L., Brill, E., Stolcke, A.: Finding consensus in speech recognition: word error minimization and other applications of confusion networks. Comput. Speech Lang. 14(4), 373\u2013400 (2000)","journal-title":"Comput. Speech Lang."},{"key":"247_CR29","doi-asserted-by":"crossref","unstructured":"Martin, A., Doddington, G., Kamm, T., Ordowski, M., Przybocki, M.: The det curve in assessment of detection task performance. In: Proceedings of Eurospeech. Rhodes, Greece, pp. 1895\u20131898 (1997)","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"247_CR30","doi-asserted-by":"crossref","unstructured":"Matsoukas, S., Bulyko, I., Xiang, B., Nguyen, K., Schwartz, R., Makhoul, J.: Integrating speech recognition and machine translation. In: Proceedings of ICASSP, pp. 1281\u20131284 (2007)","DOI":"10.1109\/ICASSP.2007.367311"},{"key":"247_CR31","doi-asserted-by":"crossref","unstructured":"Matusov, E., Hillard, D., Magimai-Doss, M., Hakkani- T\u00fcr, D.Z., Ostendorf, M., Ney, H.: Improving speech translation with automatic boundary prediction. In: INTERSPEECH, vol. 7, pp. 2449\u20132452 (2007)","DOI":"10.21437\/Interspeech.2007-644"},{"key":"247_CR32","doi-asserted-by":"crossref","unstructured":"McCallum, A., Li, W.: Early results for named entity recognition with conditional random elds, feature induction and web-enhanced lexicons. In: Proceedings of the Seventh Conference on Natural language learning at HLT-NAACL 2003, vol. 4, pp. 188\u2013191 (2003)","DOI":"10.3115\/1119176.1119206"},{"key":"247_CR33","unstructured":"Mikheev, A.: Tagging sentence boundaries. In: Proceedings of the 1st North American chapter of the Association for Computational Linguistics Conference, pp. 264\u2013271 (2000)"},{"issue":"2","key":"247_CR34","first-page":"241","volume":"23","author":"DD Palmer","year":"1997","unstructured":"Palmer, D.D., Hearst, M.A.: Adaptive multilingual sentence boundary disambiguation. Comput. Linguist. 23(2), 241\u2013267 (1997)","journal-title":"Comput. Linguist."},{"key":"247_CR35","unstructured":"Parada, C., Dredze, M., Filimonov, D., Jelinek, F.: Contextual information improves oov detection in speech. In: Proceedings of Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 216\u2013224 (2010)"},{"key":"247_CR36","doi-asserted-by":"crossref","unstructured":"Rastrow, A., Sethy, A., Ramabhadran, B.: A new method for oov detection using hybrid word\/fragment system. In: Proceedings of ICASSP, pp. 3953\u20133956 (2009)","DOI":"10.1109\/ICASSP.2009.4960493"},{"key":"247_CR37","unstructured":"Read, J., Dridan, R., Oepen, S., Solberg, L.J.: Sentence boundary detection: a long solved problem? In: Proceedings of COLING, pp. 985\u2013994 (2012)"},{"key":"247_CR38","doi-asserted-by":"crossref","unstructured":"Roark, B., Liu, Y., Harper, M., Stewart, R., Lease, M., Snover, M., Shafran, I., Dorr, B., Hale, J., Krasnyanskaya, A.K., et al.: Reranking for sentence boundary detection in conversational speech. In: Proceedings of ICASSP, vol. 1, pp. I-I (2006)","DOI":"10.1109\/ICASSP.2006.1660078"},{"key":"247_CR39","doi-asserted-by":"crossref","unstructured":"Saleem, S., Cao, H., Subramanian, K., Kamali, M., Prasad, R., Natarajan, P.: Improvements in bbn\u2019s hmmbased online arabic handwriting recognition system. In: Proceedings of Document Analysis and Recognition, the 10th International Conference on IEEE, pp. 773\u2013777 (2009)","DOI":"10.1109\/ICDAR.2009.282"},{"key":"247_CR40","doi-asserted-by":"crossref","unstructured":"Sha, F., Pereira, F.: Shallow parsing with conditional random fields. In: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, pp. 134\u2013141 (2003)","DOI":"10.3115\/1073445.1073473"},{"key":"247_CR41","unstructured":"Shen, L., Xu, J., Weischedel, R.M.: A new string-to-dependency machine translation algorithm with a target dependency language model. In: Proceedings of ACL, pp. 577\u2013585 (2008)"},{"issue":"1","key":"247_CR42","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/S0167-6393(00)00028-5","volume":"32","author":"E Shriberg","year":"2000","unstructured":"Shriberg, E., Stolcke, A., Hakkani-T\u00fcr, D., T\u00fcr, G.: Prosody-based automatic segmentation of speech into sentences and topics. Speech Commun. 32(1), 127\u2013154 (2000)","journal-title":"Speech Commun."},{"key":"247_CR43","doi-asserted-by":"crossref","unstructured":"Subramanian, K., Prasad, R., MacRostie, E., Natarajan, P.: Robust named entity detection in videotext using character lattices. In: Proceedings of ICASSP, pp. 1241\u20131244 (2008)","DOI":"10.1109\/ICASSP.2008.4517841"},{"issue":"2","key":"247_CR44","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/s10032-011-0150-z","volume":"14","author":"K Subramanian","year":"2011","unstructured":"Subramanian, K., Prasad, R., Natarajan, P.: Robust named entity detection from optical character recognition output. Int. J. Doc. Anal. Recognit. (IJDAR) 14(2), 189\u2013200 (2011)","journal-title":"Int. J. Doc. Anal. Recognit. (IJDAR)"},{"key":"247_CR45","doi-asserted-by":"crossref","unstructured":"Sun, H., Zhang, G., Zheng, F., Xu, M.: Using word confidence measure for oov words detection in a spontaneous spoken dialog system. In: Proceedings of Eurospeech. Geneva, pp. 2713\u20132716 (2003)","DOI":"10.21437\/Eurospeech.2003-523"},{"key":"247_CR46","doi-asserted-by":"crossref","unstructured":"Toselli, A.H., Vidal, E.: Fast hmm-filler approach for key word spotting in handwritten documents. In: Proceedings of ICDAR, pp. 501\u2013505 (2013)","DOI":"10.1109\/ICDAR.2013.106"},{"key":"247_CR47","unstructured":"Touir, A.A., Mathkour, H., Al-Sanea, W.: Semantic-based segmentation of arabic texts. Inf. Technol. J. 7, 1009\u20131015 (2008)"},{"key":"247_CR48","unstructured":"Tseng, H.: A conditional random field word segmenter. In: Proceedings of the Fourth SIGHAN Workshop on Chinese Language Processing (2005)"},{"key":"247_CR49","unstructured":"Walker, D.J., Clements, D.E., Darwin, M., Amtrup, J.W.: Sentence boundary detection: a comparison of paradigms for improving mt quality. In: Proceedings of the MT Summit VIII (2001)"},{"key":"247_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, H., Liu, C.L.: A lattice-based method for keyword spotting in online chinese handwriting. In: Proceedings of ICDAR, pp. 1064\u20131068 (2011)","DOI":"10.1109\/ICDAR.2011.215"},{"key":"247_CR51","unstructured":"Zimmermann, M.: Sentence boundary detection for handwritten text recognition. In: Proceedings of the Tenth International Workshop on Frontiers in Handwriting Recognition. Suvisoft (2006)"},{"key":"247_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, B., Besacier, L., Gao, Y.: On efficient coupling of asr and smt for speech translation. In: Proceedings of ICASSP, vol. 4, pp. IV-101 (2007)","DOI":"10.1109\/ICASSP.2007.367173"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-015-0247-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-015-0247-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-015-0247-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-015-0247-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T03:32:40Z","timestamp":1748403160000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-015-0247-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5,28]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2015,9]]}},"alternative-id":["247"],"URL":"https:\/\/doi.org\/10.1007\/s10032-015-0247-x","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,5,28]]},"assertion":[{"value":"12 November 2013","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2015","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2015","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2015","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}