{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:12:50Z","timestamp":1773083570591,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2004,8,22]],"date-time":"2004-08-22T00:00:00Z","timestamp":1093132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2004,8,22]]},"DOI":"10.1145\/1014052.1014058","type":"proceedings-article","created":{"date-parts":[[2004,10,7]],"date-time":"2004-10-07T17:39:48Z","timestamp":1097170788000},"page":"20-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":75,"title":["Mining reference tables for automatic text segmentation"],"prefix":"10.1145","author":[{"given":"Eugene","family":"Agichtein","sequence":"first","affiliation":[{"name":"Columbia University"}]},{"given":"Venkatesh","family":"Ganti","sequence":"additional","affiliation":[{"name":"Microsoft Research"}]}],"member":"320","published-online":{"date-parts":[[2004,8,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Microsoft SmartTagger.  Microsoft SmartTagger."},{"key":"e_1_3_2_1_2_1","volume-title":"7th Message Understanding Conference (MUC-7). Morgan Kaufman","year":"1998","unstructured":"Proceedings of the 7th Message Understanding Conference (MUC-7). Morgan Kaufman , 1998 . Proceedings of the 7th Message Understanding Conference (MUC-7). Morgan Kaufman, 1998."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/276304.276330"},{"key":"e_1_3_2_1_4_1","volume-title":"UWEETR-2002-0003","author":"Bilmes J.","year":"2002","unstructured":"J. Bilmes . What HMMs can do. Technical report , UWEETR-2002-0003 , 2002 . J. Bilmes. What HMMs can do. Technical report, UWEETR-2002-0003, 2002."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/375663.375682"},{"key":"e_1_3_2_1_6_1","volume-title":"Sixteenth National Conference on Artificial Intelligence","author":"Califf M. E.","year":"1999","unstructured":"M. E. Califf and R. J. Mooney . Relational learning of pattern-match rules for information extraction . In Sixteenth National Conference on Artificial Intelligence , 1999 . M. E. Califf and R. J. Mooney. Relational learning of pattern-match rules for information extraction. In Sixteenth National Conference on Artificial Intelligence, 1999."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872796"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/981863.981904"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014065"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3115\/1118693.1118694"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Collins M.","year":"1999","unstructured":"M. Collins and Y. Singer . Unsupervised models for named entity classification . In Proceedings of the Conference on Empirical Methods in Natural Language Processing , 1999 . M. Collins and Y. Singer. Unsupervised models for named entity classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, 1999."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the VLDB Conference","author":"Crescenzi V.","year":"2001","unstructured":"V. Crescenzi , G. Mecca , and P. Merialdo . RoadRunner: Towards automatic data extraction from large web sites . In Proceedings of the VLDB Conference , 2001 . V. Crescenzi, G. Mecca, and P. Merialdo. RoadRunner: Towards automatic data extraction from large web sites. In Proceedings of the VLDB Conference, 2001."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the Eurospeech Conference","author":"Droppo J.","year":"2001","unstructured":"J. Droppo , L. Deng , and A. Acero . Evaluation of the splice algorithm on the aurora2 database . In Proceedings of the Eurospeech Conference , 2001 . J. Droppo, L. Deng, and A. Acero. Evaluation of the splice algorithm on the aurora2 database. In Proceedings of the Eurospeech Conference, 2001."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/304182.304223"},{"key":"e_1_3_2_1_15_1","first-page":"584","volume-title":"Proceedings of the AAAI\/IAAI Conference","author":"Freitag D.","year":"2000","unstructured":"D. Freitag and A. McCallum . Information extraction with HMM structures learned by stochastic optimization . In Proceedings of the AAAI\/IAAI Conference , pages 584 -- 589 , 2000 . D. Freitag and A. McCallum. Information extraction with HMM structures learned by stochastic optimization. In Proceedings of the AAAI\/IAAI Conference, pages 584--589, 2000."},{"key":"e_1_3_2_1_16_1","first-page":"584","volume-title":"Proceedings of the AAAI\/IAAI Conference","author":"Freitag D.","year":"2000","unstructured":"D. Freitag and A. McCallum . Information extraction with HMM structures learned by stochastic optimization . In Proceedings of the AAAI\/IAAI Conference , pages 584 -- 589 , 2000 . D. Freitag and A. McCallum. Information extraction with HMM structures learned by stochastic optimization. In Proceedings of the AAAI\/IAAI Conference, pages 584--589, 2000."},{"key":"e_1_3_2_1_17_1","volume-title":"Information Extraction (International Summer School SCIE-97)","author":"Grishman R.","year":"1997","unstructured":"R. Grishman . Information extraction: Techniques and challenges . In Information Extraction (International Summer School SCIE-97) . Springer-Verlag , 1997 . R. Grishman. Information extraction: Techniques and challenges. In Information Extraction (International Summer School SCIE-97). Springer-Verlag, 1997."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009761603038"},{"issue":"4","key":"e_1_3_2_1_19_1","first-page":"33","article-title":"Accurately and reliably extracting data from the web: A machine learning approach","volume":"23","author":"Knoblock C. A.","year":"2000","unstructured":"C. A. Knoblock , K. Lerman , S. Minton , and I. Muslea . Accurately and reliably extracting data from the web: A machine learning approach . IEEE Data Engineering Bulletin , 23 ( 4 ): 33 -- 41 , 2000 . C. A. Knoblock, K. Lerman, S. Minton, and I. Muslea. Accurately and reliably extracting data from the web: A machine learning approach. IEEE Data Engineering Bulletin, 23(4):33--41, 2000.","journal-title":"IEEE Data Engineering Bulletin"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075165"},{"key":"e_1_3_2_1_21_1","volume-title":"NIST 2003 language recognition evaluation. In Proceedings of the Eurospeech Conference","author":"Martin A.","year":"2003","unstructured":"A. Martin and M. Przybocki . NIST 2003 language recognition evaluation. In Proceedings of the Eurospeech Conference , 2003 . A. Martin and M. Przybocki. NIST 2003 language recognition evaluation. In Proceedings of the Eurospeech Conference, 2003."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the ICML Conference","author":"McCallum A.","year":"2000","unstructured":"A. McCallum , D. Freitag , and F. Pereira . Maximum entropy markov models for information extraction and segmentation . In Proceedings of the ICML Conference , 2000 . A. McCallum, D. Freitag, and F. Pereira. Maximum entropy markov models for information extraction and segmentation. In Proceedings of the ICML Conference, 2000."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/977035.977037"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/301136.301191"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"e_1_3_2_1_26_1","volume-title":"Fundamentals of speech recognition","author":"Rabiner L. R.","year":"1993","unstructured":"L. R. Rabiner and B. H. Juang . Fundamentals of speech recognition . Prentice Hall , 1993 . L. R. Rabiner and B. H. Juang. Fundamentals of speech recognition. Prentice Hall, 1993."},{"key":"e_1_3_2_1_27_1","volume-title":"AAAI 99 Workshop on Machine Learning for Information Extraction","author":"Seymore K.","year":"1999","unstructured":"K. Seymore , A. McCallum , and R. Rosenfeld . Learning hidden Markov model structure for information extraction . In AAAI 99 Workshop on Machine Learning for Information Extraction , 1999 . K. Seymore, A. McCallum, and R. Rosenfeld. Learning hidden Markov model structure for information extraction. In AAAI 99 Workshop on Machine Learning for Information Extraction, 1999."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015422"}],"event":{"name":"KDD04: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","location":"Seattle WA USA","acronym":"KDD04","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","ACM Association for Computing Machinery"]},"container-title":["Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1014052.1014058","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1014052.1014058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T16:31:29Z","timestamp":1750264289000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1014052.1014058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004,8,22]]},"references-count":28,"alternative-id":["10.1145\/1014052.1014058","10.1145\/1014052"],"URL":"https:\/\/doi.org\/10.1145\/1014052.1014058","relation":{},"subject":[],"published":{"date-parts":[[2004,8,22]]},"assertion":[{"value":"2004-08-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}