{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:33:59Z","timestamp":1761395639833,"version":"3.41.0"},"publisher-location":"New York, New York, USA","reference-count":21,"publisher":"ACM Press","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1145\/3368926.3369716","type":"proceedings-article","created":{"date-parts":[[2019,12,20]],"date-time":"2019-12-20T13:30:11Z","timestamp":1576848611000},"page":"322-327","source":"Crossref","is-referenced-by-count":5,"title":["Punctuation Prediction for Vietnamese Texts Using Conditional Random Fields"],"prefix":"10.1145","author":[{"given":"Quang H.","family":"Pham","sequence":"first","affiliation":[{"name":"School of Information System, Singapore Management University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binh T.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"AISIA Research Lab, VNU HCM - University of Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nguyen Viet","family":"Cuong","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","reference":[{"key":"key-10.1145\/3368926.3369716-1","unstructured":"Doug Beeferman, Adam Berger, and John Lafferty. 1998. Cyberpunc: A lightweight punctuation annotation system for speech. In IEEE International Conference on Acoustics, Speech and Signal Processing."},{"key":"key-10.1145\/3368926.3369716-2","unstructured":"Eunah Cho, Jan Niehues, and Alex Waibel. 2012. Segmentation and punctuation prediction in speech language translation using a monolingual translation system.. In Workshop on Spoken Language Translation."},{"key":"key-10.1145\/3368926.3369716-3","unstructured":"Nguyen Viet Cuong, Nan Ye, Wee Sun Lee, and Hai Leong Chieu. 2014. Conditional Random Field with High-order Dependencies for Sequence Labeling and Segmentation. Journal of Machine Learning Research 15 (2014), 981--1009."},{"key":"key-10.1145\/3368926.3369716-4","unstructured":"Manning D. Christopher, Raghavan Prabhakar, and Schacetzel Hinrich. 2008. An Introduction to Information Retrieval. Cambridge, UK: Cambridge University Press."},{"key":"key-10.1145\/3368926.3369716-5","unstructured":"Dinh Dien, Hoang Kiem, and Nguyen Van Toan. 2001. Vietnamese word segmentation. In Natural Language Processing Pacific Rim Symposium."},{"key":"key-10.1145\/3368926.3369716-6","doi-asserted-by":"crossref","unstructured":"Jing Huang and Geoffrey Zweig. 2002. Maximum entropy model for punctuation annotation from speech. In International Conference on Spoken Language Processing.","DOI":"10.21437\/ICSLP.2002-307"},{"key":"key-10.1145\/3368926.3369716-7","unstructured":"Taku Kudo. 2005. CRF++: Yet another CRF toolkit. Software available at http:\/\/crfpp.sourceforge.net (2005)."},{"key":"key-10.1145\/3368926.3369716-8","unstructured":"John Lafferty, Andrew McCallum, and Fernando C.N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In International Conference on Machine Learning."},{"key":"key-10.1145\/3368926.3369716-9","unstructured":"Wei Lu and Hwee Tou Ng. 2010. Better Punctuation Prediction with Dynamic Conditional Random Fields. In Conference on Empirical Methods in Natural Language Processing."},{"key":"key-10.1145\/3368926.3369716-10","doi-asserted-by":"crossref","unstructured":"Andrew McCallum and Wei Li. 2003. Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons. In Conference on Natural Language Learning.","DOI":"10.3115\/1119176.1119206"},{"key":"key-10.1145\/3368926.3369716-11","unstructured":"Cam-Tu Nguyen, Trung-Kien Nguyen, Xuan-Hieu Phan, Le-Minh Nguyen, and Quang-Thuy Ha. 2006. Vietnamese word segmentation with CRFs and SVMs: An investigation. In Pacific Asia Conference on Language, Information and Computation."},{"key":"key-10.1145\/3368926.3369716-12","unstructured":"Michael Paul. 2009. Overview of the IWSLT 2009 evaluation campaign. In Workshop on Spoken Language Translation."},{"key":"key-10.1145\/3368926.3369716-13","unstructured":"Michael Paul. 2009. Overview of the IWSLT 2009 evaluation campaign. International Workshop on Spoken Language Translation (IWSLT) 2009, 1--18 (2009)."},{"key":"key-10.1145\/3368926.3369716-14","unstructured":"Stephan Peitz, Markus Freitag, Arne Mauser, and Hermann Ney. 2011. Modeling punctuation prediction as machine translation. In IWSLT."},{"key":"key-10.1145\/3368926.3369716-15","unstructured":"Lawrence Rabiner. 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77, 2 (1989), 257--286."},{"key":"key-10.1145\/3368926.3369716-16","doi-asserted-by":"crossref","unstructured":"Fei Sha and Fernando Pereira. 2003. Shallow parsing with conditional random fields. In Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology.","DOI":"10.3115\/1073445.1073473"},{"key":"key-10.1145\/3368926.3369716-17","unstructured":"Strassel Stephanie, Junbo Kong, and David Graff. 2005. TDT4 Multilingual Text and Annotations LDC2005T16. Web Download. Philadelphia: Linguistic Data Consortium."},{"key":"key-10.1145\/3368926.3369716-18","unstructured":"Charles Sutton and Andrew McCallum. 2006. An introduction to conditional random fields for relational learning. Introduction to Statistical Relational Learning (2006), 93--128."},{"key":"key-10.1145\/3368926.3369716-19","doi-asserted-by":"crossref","unstructured":"Oanh Thi Tran, Cuong Anh Le, Thuy Quang Ha, and Quynh Hoang Le. 2009. An experimental study on Vietnamese POS tagging. In International Conference on Asian Language Processing.","DOI":"10.1109\/IALP.2009.14"},{"key":"key-10.1145\/3368926.3369716-20","unstructured":"Dongdong Zhang, Shuangzhi Wu, Nan Yang, and Mu Li. 2013. Punctuation Prediction with Transition-based Parsing. In ACL."},{"key":"key-10.1145\/3368926.3369716-21","unstructured":"Yanqing Zhao, Chaoyue Wang, and Guohong Fu. 2012. A CRF sequence labeling approach to Chinese punctuation prediction. In Pacific Asia Conference on Language, Information and Computation."}],"event":{"number":"10","sponsor":["SOICT, School of Information and Communication Technology - HUST","NAFOSTED, The National Foundation for Science and Technology Development"],"acronym":"SoICT 2019","name":"the Tenth International Symposium","start":{"date-parts":[[2019,12,4]]},"location":"Hanoi, Ha Long Bay, Viet Nam","end":{"date-parts":[[2019,12,6]]}},"container-title":["Proceedings of the Tenth International Symposium on Information and Communication Technology - SoICT 2019"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3368926.3369716","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/dl.acm.org\/ft_gateway.cfm?id=3369716&ftid=2101290&dwn=1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:05Z","timestamp":1750204385000},"score":1,"resource":{"primary":{"URL":"http:\/\/dl.acm.org\/citation.cfm?doid=3368926.3369716"}},"subtitle":[],"proceedings-subject":"Information and Communication Technology","short-title":[],"issued":{"date-parts":[[2019]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1145\/3368926.3369716","relation":{},"subject":[],"published":{"date-parts":[[2019]]}}}