{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T05:38:41Z","timestamp":1778218721131,"version":"3.51.4"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,7,22]],"date-time":"2017-07-22T00:00:00Z","timestamp":1500681600000},"content-version":"unspecified","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":[[2018,3]]},"DOI":"10.1007\/s10579-017-9398-3","type":"journal-article","created":{"date-parts":[[2017,7,22]],"date-time":"2017-07-22T08:11:37Z","timestamp":1500711097000},"page":"269-315","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Ensuring annotation consistency and accuracy for Vietnamese treebank"],"prefix":"10.1007","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8185-4312","authenticated-orcid":false,"given":"Quy T.","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Miyao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ha T. T.","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nhung T. H.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,7,22]]},"reference":[{"key":"9398_CR1","unstructured":"Abeill\u00e9, A., Cl\u00e9ment, L., & Toussenel, F. (2003). Building a treebank for french. In Treebanks (pp. 165\u2013187). New York: Springer."},{"key":"9398_CR2","doi-asserted-by":"crossref","unstructured":"Allauzen, A., Aufrant, L., Burlot, F., Knyazeva, E., Lavergne, T., & Yvon, F. (2016). Limsi@ wmt\u201916: Machine translation of news. In Proceedings of the first conference on machine translation (pp. 239\u2013245). Association for Computational Linguistics.","DOI":"10.18653\/v1\/W16-2304"},{"key":"9398_CR3","doi-asserted-by":"crossref","unstructured":"Barr, C., Jones, R., & Regelson, M. (2008). The linguistic structure of English web-search queries. In Proceedings of the conference on empirical methods in natural language processing (pp. 1021\u20131030). Association for Computational Linguistics.","DOI":"10.3115\/1613715.1613848"},{"key":"9398_CR38","volume-title":"Bracketing guidelines for treebank II style penn treebank project","author":"A Bies","year":"1995","unstructured":"Bies, A., Ferguson, M., Katz, K., MacIntyre, R., Tredinnick, V., Kim, G., et al. (1995). Bracketing guidelines for treebank II style penn treebank project. Philadelphia: University of Pennsylvania."},{"key":"9398_CR4","doi-asserted-by":"crossref","unstructured":"Cai, J., Utiyama, M., Sumita, E., & Zhang, Y. (2014). Dependency-based pre-ordering for Chinese\u2013English machine translation. In Proceedings of the 52nd annual meeting of the association for computational linguistics (pp. 155\u2013160). Association for Computational Linguistics.","DOI":"10.3115\/v1\/P14-2026"},{"key":"9398_CR5","doi-asserted-by":"crossref","unstructured":"Chang, P. C., Galley, M., & Manning, C. D. (2008). Optimizing Chinese word segmentation for machine translation performance. In Proceedings of the third workshop on statistical machine translation (pp. 224\u2013232). Association for Computational Linguistics.","DOI":"10.3115\/1626394.1626430"},{"key":"9398_CR6","doi-asserted-by":"crossref","unstructured":"Chinkina, M., Kannan, M., & Meurers, D. (2016). Online information retrieval for language learning. In Proceedings of the 54th annual meeting of the association for computational linguistics-system demonstrations (pp. 7\u201312).","DOI":"10.18653\/v1\/P16-4002"},{"key":"9398_CR7","unstructured":"Corp, D.C.S. LacViet. (2011). Vietnamese dictionary. LacViet Corp."},{"key":"9398_CR40","volume-title":"Vietnamese grammar","author":"Q-B Diep","year":"2005","unstructured":"Diep, Q.-B. (2005). Vietnamese grammar. Ha Noi: Vietnam Education Publisher."},{"key":"9398_CR8","doi-asserted-by":"crossref","unstructured":"Dinh, D., & Vu, T. (2006). A maximum entropy approach for Vietnamese word segmentation. In Proceedings of research, innovation and vision for the future in computing and communication technologies (pp. 248\u2013253). IEEE.","DOI":"10.1109\/RIVF.2006.1696447"},{"key":"9398_CR39","volume-title":"On the definition of word","author":"AM Sciullo Di","year":"1987","unstructured":"Di Sciullo, A. M., & Williams, E. (1987). On the definition of word (Vol. 14). New York: Springer."},{"key":"9398_CR9","unstructured":"Fang, A. C., & Cao, J. (2010). Enhanced genre classification through linguistically fine-grained pos tags. In Proceedings of paclic (pp. 85\u201394)."},{"key":"9398_CR10","unstructured":"Galitsky, B., Ilvovsky, D. I., Kuznetsov, S. O. & Strok, F. (2013). Matching sets of parse trees for answering multi-sentence questions. In Proceedings of RANLP (pp. 285\u2013293)."},{"key":"9398_CR11","doi-asserted-by":"crossref","unstructured":"Han, C. H., Han, N. R., Ko, E. S., & Palmer, M. (2002). Development and evaluation of a Korean treebank and its application to NLP. In Proceedings of the 3rd international conference on language resources and evaluation (LREC-2002) (pp. 1635\u20131642).","DOI":"10.29403\/LI.6.1.7"},{"key":"9398_CR41","volume-title":"Vietnamese dictionary","author":"P Hoang","year":"1998","unstructured":"Hoang, P. (1998). Vietnamese dictionary. Singapore: Scientific & Technical Publishing."},{"key":"9398_CR12","doi-asserted-by":"crossref","unstructured":"Hoshino, S., Miyao, Y., Sudoh, K., Hayashi, K., & Nagata, M. (2015). Discriminative preordering meets Kendall\u2019s tau maximization. In Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (short papers) (pp. 139\u2013144). Association for Computational Linguistics.","DOI":"10.3115\/v1\/P15-2023"},{"key":"9398_CR13","doi-asserted-by":"crossref","unstructured":"Jijkoun, V., De\u00a0Rijke, M., & Mur, J. (2004). Information extraction for question answering: Improving recall through syntactic patterns. In Proceedings of the 20th international conference on computational linguistics (pp. 1284). Association for Computational Linguistics.","DOI":"10.3115\/1220355.1220543"},{"key":"9398_CR14","unstructured":"Katz-Brown, J., Petrov, S., McDonald, R., Och, F., Talbot, D., Ichikawa, H., Seno, M., & Kazawa, H. (2011). Training a parser for machine translation reordering. In Proceedings of the conference on empirical methods in natural language processing (pp. 183\u2013192). Association for Computational Linguistics."},{"key":"9398_CR15","unstructured":"Le, H. P., Nguyen, T. M. H., & Roussanaly, A. (2012). Vietnamese parsing with an automatically extracted tree-adjoining grammar. In Proceedings of research, innovation and vision for the future in computing and communication technologies (RIVF) (pp. 1\u20136). IEEE."},{"key":"9398_CR16","doi-asserted-by":"crossref","unstructured":"Le, A. C., Nguyen, P. T., Vuong, H. T., Pham, M. T., & Ho, T. B. (2009). An experimental study on lexicalized statistical parsing for Vietnamese. In Proceedings of knowledge and systems engineering (pp. 162\u2013167). IEEE.","DOI":"10.1109\/KSE.2009.41"},{"key":"9398_CR17","doi-asserted-by":"crossref","unstructured":"Le-Hong Phuong, N. T. M., Huyen, A. R., & Vinh, H. T. (2008). A hybrid approach to word segmentation of Vietnamese texts. In Proceedings of the 2nd international conference on language and automata theory and applications.","DOI":"10.1007\/978-3-540-88282-4_23"},{"key":"9398_CR18","unstructured":"Le-Hong, P., Roussanaly, A., Nguyen, T. M. H., & Rossignol, M. (2010). An empirical study of maximum entropy approach for part-of-speech tagging of Vietnamese texts. In Traitement Automatique des Langues Naturelles-taln 2010 (pp. 12)."},{"issue":"2","key":"9398_CR42","first-page":"313","volume":"19","author":"MP Marcus","year":"1993","unstructured":"Marcus, M. P., Marcinkiewicz, M. A., & Santorini, B. (1993). Building a large annotated corpus of english: The penn treebank. Computational Linguistics, 19(2), 313\u2013330.","journal-title":"Computational Linguistics"},{"issue":"1","key":"9398_CR43","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1162\/coli.2008.34.1.35","volume":"34","author":"Y Miyao","year":"2008","unstructured":"Miyao, Y., & Tsujii, J. (2008). Feature forest models for probabilistic HPSG parsing. Computational Linguistics, 34(1), 35\u201380.","journal-title":"Computational Linguistics"},{"key":"9398_CR19","doi-asserted-by":"crossref","unstructured":"Nghiem, M., Dinh, D., & Nguyen, M. (2008). Improving Vietnamese POS tagging by integrating a rich feature set and support vector machines. In Proceedings of research, innovation and vision for the future in computing and communication technologies (RIVF) (pp. 128\u2013133). IEEE.","DOI":"10.1109\/RIVF.2008.4586344"},{"key":"9398_CR20","unstructured":"Nguyen, T. M. H., Hoang, T. T. L., & Vu, X. L. (2010). Vietnamese word segmentation guidelines. Technical report sp 8.2. Ministry of Education and Training (Vietnam)."},{"key":"9398_CR21","unstructured":"Nguyen, Q. T., Miyao, Y., Le, H. T. T., & Nguyen, N. L. T. (2016). Challenges and solutions for consistent annotation of Vietnamese treebank. In Proceedings of the language resources and evaluation conference."},{"key":"9398_CR22","unstructured":"Nguyen, Q. T., Nguyen, N. L. T., & Miyao, Y. (2012). Comparing different criteria for Vietnamese word segmentation. In Proceedings of 3rd workshop on south and southeast asian natural language processing (SANLP) (pp. 53\u201368). Citeseer."},{"key":"9398_CR23","unstructured":"Nguyen, Q. T., Nguyen, N. L. T., & Miyao, Y. (2013). Utilizing state-of-the-art parsers to diagnose problems in treebank annotation for a less resourced language. In Proceedings of the 7th linguistic annotation workshop & interoperability with discourse (pp. 19\u201327). Association for Computational Linguistics."},{"key":"9398_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, Q. D., Nguyen, Q. D., Pham, B. S., Nguyen, P. T., & Nguyen, L. M. (2014). From treebank conversion to automatic dependency parsing for Vietnamese. In Natural language processing and information systems (pp. 196\u2013207). New York: Springer.","DOI":"10.1007\/978-3-319-07983-7_26"},{"issue":"3","key":"9398_CR44","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1007\/s10579-015-9308-5","volume":"49","author":"PT Nguyen","year":"2015","unstructured":"Nguyen, P. T., Le, A. C., Ho, T. B., & Nguyen, V. H. (2015). Vietnamese treebank construction and entropy-based error detection. Language Resources and Evaluation, 49(3), 487\u2013519.","journal-title":"Language Resources and Evaluation"},{"key":"9398_CR25","unstructured":"Nguyen, P. T., Vu, X. L., & Nguyen, T. M. H. (2010a). Vietnamese part-of-speech tagging guidelines. Technical report sp 7.3. Ministry of Education and Training (Vietnam)."},{"key":"9398_CR26","doi-asserted-by":"crossref","unstructured":"Nguyen, P. T., Vu, X. L., Nguyen, T. M. H., Nguyen, V. H., & Le, H. P. (2009). Building a large syntactically-annotated corpus of Vietnamese. In Proceedings of the third linguistic annotation workshop (pp. 182\u2013185). Association for Computational Linguistics.","DOI":"10.3115\/1698381.1698416"},{"key":"9398_CR27","unstructured":"Nguyen, P. T., Vu, X. L, Nguyen, T. M. H., Dao, M. T., Dao, T. M. N., Le, K. N. (2010b). Vietnamese bracketing guidelines. Technical report sp7.3. Ministry of Education and Training (Vietnam)."},{"issue":"3","key":"9398_CR45","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1108\/00220410710743306","volume":"63","author":"F Peng","year":"2007","unstructured":"Peng, F., & Huang, X. (2007). Machine learning for asian language text classification. Journal of Documentation, 63(3), 378\u2013397.","journal-title":"Journal of Documentation"},{"key":"9398_CR28","doi-asserted-by":"crossref","unstructured":"Petrov, S., Barrett, L., Thibaux, R., & Klein, D. (2006). Learning accurate, compact, and interpretable tree annotation. In Proceedings of the 21st international conference on computational linguistics and the 44th annual meeting of the association for computational linguistics (pp. 433\u2013440). Association for Computational Linguistics.","DOI":"10.3115\/1220175.1220230"},{"key":"9398_CR46","volume-title":"Part-of-speech tagging guidelines for the penn treebank project","author":"B Santorini","year":"1990","unstructured":"Santorini, B. (1990). Part-of-speech tagging guidelines for the penn treebank project. Pennsylvania: University of Pennsylvania."},{"key":"9398_CR29","unstructured":"SCSSV. (1983). Vietnamese grammar. Social Sciences Publishers."},{"key":"9398_CR30","unstructured":"Socher, R., Bauer, J., Manning, C. D., & Ng, A. Y. (2013). Parsing with compositional vector grammars. In Proceedings of the ACL conference. Citeseer."},{"key":"9398_CR31","doi-asserted-by":"crossref","unstructured":"Toutanova, K., Klein, D., Manning, C. D., & Singer, Y. (2003). Feature-rich part-of-speech tagging with a cyclic dependency network. In Proceedings of the 2003 conference of the north american chapter of the association for computational linguistics on human language technology (Vol. 1, pp. 173\u2013180). Association for Computational Linguistics.","DOI":"10.3115\/1073445.1073478"},{"key":"9398_CR32","unstructured":"Tsuruoka, Y., Miyao, Y., & Kazama, J. (2011). Learning with lookahead: Can history-based models rival globally optimized models? In Proceedings of the fifteenth conference on computational natural language learning (pp. 238\u2013246). Association for Computational Linguistics."},{"key":"9398_CR33","unstructured":"Verberne, S., Boves, L., Oostdijk, N., & Coppen, P. A. (2008). Using syntactic information for improving why-question answering. In Proceedings of the 22nd international conference on computational linguistics (Vol. 1, pp. 953\u2013960). Association for Computational Linguistics."},{"key":"9398_CR34","unstructured":"Xia, F. (2000a). The part-of-speech tagging guidelines for the penn Chinese treebank (3.0). Technical report IRCS 00-07. University of Pennsylvania."},{"key":"9398_CR35","unstructured":"Xia, F. (2000b). The segmentation guidelines for the penn Chinese treebank (3.0). Technical report IRCS 00-06. University of Pennsylvania."},{"key":"9398_CR36","unstructured":"Xia, F., Palmer, M., Xue, N., Okurowski, M. E., Kovarik, J., Chiou, F. D., Huang, S., Kroch, T., & Marcus, M. P. (2000). Developing guidelines and ensuring consistency for Chinese text annotation. In Proceedings of the second international conference on language resources and evaluation."},{"issue":"02","key":"9398_CR47","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1017\/S135132490400364X","volume":"11","author":"N Xue","year":"2005","unstructured":"Xue, N., Xia, F., Chiou, F.-D., & Palmer, M. (2005). The penn chinese treebank: Phrase structure annotation of a large corpus. Natural Language Eengineering, 11(02), 207\u2013238.","journal-title":"Natural Language Eengineering"},{"key":"9398_CR37","unstructured":"Xue, N., Xia, F., Huang, S., & Kroch, A. (2000). The bracketing guidelines for the penn Chinese treebank (3.0). Technical report IRCS 00-08. University of Pennsylvania."}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-017-9398-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-017-9398-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-017-9398-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T07:20:21Z","timestamp":1569914421000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-017-9398-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,22]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,3]]}},"alternative-id":["9398"],"URL":"https:\/\/doi.org\/10.1007\/s10579-017-9398-3","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,22]]}}}