{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T14:49:45Z","timestamp":1780670985359,"version":"3.54.1"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T00:00:00Z","timestamp":1697760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["MOST-107-2201-E-004-009-MY3"],"award-info":[{"award-number":["MOST-107-2201-E-004-009-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016848","name":"National Chengchi University","doi-asserted-by":"publisher","award":["110H124D-03"],"award-info":[{"award-number":["110H124D-03"]}],"id":[{"id":"10.13039\/100016848","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Words are essential parts for understanding classical Chinese poems. We report a collection of 32,399 classical Chinese poems that were annotated with word boundaries. Statistics about the annotated poems support a few heuristic experiences, including the patterns of lines and a practice for the parallel structures (\u5c0d\u4ed7), that researchers of Chinese literature discuss in the literature. The annotators were affiliated with two universities, so they could annotate the poems as independently as possible. Results of an inter-rater agreement study indicate that the annotators have consensus over the identified words 93 per cent of the time and have perfect consensus for the segmentation of a poem 42 per cent of the time. We applied unsupervised classification methods to annotate the poems in several different settings, and evaluated the results with human annotations. Under favorable conditions, the classifier identified about 88 per cent of the words, and segmented poems perfectly 22 per cent of the time.<\/jats:p>","DOI":"10.1093\/llc\/fqad073","type":"journal-article","created":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T18:26:48Z","timestamp":1697826408000},"page":"228-241","source":"Crossref","is-referenced-by-count":1,"title":["Machine learning and data analysis for word segmentation of classical Chinese poems: illustrations with Tang and Song examples"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4093-1497","authenticated-orcid":false,"given":"Chao-Lin","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science, National Chengchi University , 64 Chih-Nan Road Section 2 , Wen-Shan, Taipei 116011, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Ting","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California at Riverside , 900 University Avenue , Riverside, California 92521, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Ting","family":"Chu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Yang Ming Chiao Tung University , 1001 University Road , East, Hsinchu 300093, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ti-Yong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Chengchi University , 64 Chih-Nan Road Section 2 , Wen-Shan, Taipei 116011, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,10,20]]},"reference":[{"key":"2024040210375490600_fqad073-B1","volume-title":"Introduction to Machine Learning","author":"Alpaydin","year":"2020","edition":"4th edn."},{"key":"2024040210375490600_fqad073-B2","article-title":"Reading the Quan Tang shi: Literary History, Topic Modeling, Divergence Measures\u2019","volume":"13","author":"Broadwell","year":"2019","journal-title":"Digital Humanities Quarterly"},{"key":"2024040210375490600_fqad073-B3","first-page":"101","author":"Chen","year":"1992"},{"key":"2024040210375490600_fqad073-B4","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/MIS.2015.71","article-title":"A Boundary Assembling Method for Chinese Entity-mention Recognition\u2019","volume":"30","author":"Chen","year":"2015","journal-title":"IEEE Intelligent Systems"},{"key":"2024040210375490600_fqad073-B5","volume-title":"Elements of Information Theory","author":"Cover","year":"2006","edition":"2nd edn"},{"key":"2024040210375490600_fqad073-B6","doi-asserted-by":"crossref","first-page":"6154","DOI":"10.1073\/pnas.1516510113","article-title":"On the Unsupervised Analysis of Domain-specific Chinese Texts\u2019","volume":"113","author":"Deng","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2024040210375490600_fqad073-B7","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the Amount of Ecologic Association between Species\u2019","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"key":"2024040210375490600_fqad073-B8","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1093\/biomet\/40.3-4.237","article-title":"The Population Frequencies of Species and the Estimation of Population Parameters\u2019","volume":"40","author":"Good","year":"1953","journal-title":"Biometrika"},{"key":"2024040210375490600_fqad073-B9","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"2024040210375490600_fqad073-B10","first-page":"727","article-title":"The Computer Aided Research Work of Chinese Ancient Poems (\u5510\u5b8b\u8bd7\u4e4b\u8ba1\u7b97\u673a\u8f85\u52a9\u6df1\u5c42\u7814\u7a76","volume":"37","author":"Hu","year":"2001","journal-title":"Acta Scientiarum Naturalium Universitatis Pekinensis (\u5317\u4eac\u5927\u5b66\u5b66\u62a5(\u81ea\u7136\u79d1\u5b66\u7248"},{"key":"2024040210375490600_fqad073-B11","volume-title":"Tangyin Tongqian (\u5510\u97f3\u7d71\u7c3d) (reprint).","author":"Hu","year":"2003"},{"key":"2024040210375490600_fqad073-B12","first-page":"69","author":"Huang","year":"2007"},{"key":"2024040210375490600_fqad073-B13","volume-title":"A Linguistic Research for Tang Poems (\u5510\u8a69\u8a9e\u8a00\u7814\u7a76).","author":"Jiang","year":"2008"},{"key":"2024040210375490600_fqad073-B14","first-page":"82","article-title":"Syntactic Patterns in Classical Chinese Poems: A Quantitative Study\u2019","volume":"33","author":"Lee","year":"2018","journal-title":"Digital Scholarship in the Humanities"},{"key":"2024040210375490600_fqad073-B15","author":"Liu","year":"2019"},{"key":"2024040210375490600_fqad073-B16","first-page":"231","author":"Liu","year":"2018"},{"key":"2024040210375490600_fqad073-B17","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1215\/23290048-7257002","article-title":"Exploring Chinese Poetry with Digital Assistance: Examples from Linguistic, Literary, and Historical Viewpoints\u2019","volume":"5","author":"Liu","year":"2018","journal-title":"Journal of Chinese Literature and Culture"},{"key":"2024040210375490600_fqad073-B18","author":"Liu","year":"2020"},{"key":"2024040210375490600_fqad073-B19","first-page":"507","author":"Liu","year":"2017"},{"key":"2024040210375490600_fqad073-B20","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.neucom.2019.01.078","article-title":"Bidirectional LSTM with Attention Mechanism and Convolutional Layer for Text Classification\u2019","volume":"337","author":"Liu","year":"2019","journal-title":"Neurocomputing"},{"key":"2024040210375490600_fqad073-B21","author":"Lo","year":"2005"},{"key":"2024040210375490600_fqad073-B22","first-page":"168","author":"Ma","year":"2003"},{"key":"2024040210375490600_fqad073-B23","volume-title":"Foundations of Statistical Natural Language Processing","author":"Manning","year":"1999"},{"key":"2024040210375490600_fqad073-B24","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1353\/tan.2007.0003","article-title":"A Tang Version of Du Fu: The Tangshi Leixuan\u2019","volume":"25","author":"Owen","year":"2007","journal-title":"Tang Studies"},{"key":"2024040210375490600_fqad073-B25","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1093\/llc\/fqaa062","article-title":"\u201cUniformity\u201d or \u201cDispersion\u201d?\u2014The Evolution of Chinese poetic Word Categories\u2019 Distribution Patterns","volume":"36","author":"Pan","year":"2021","journal-title":"Digital Scholarship in the Humanities"},{"key":"2024040210375490600_fqad073-B26","first-page":"117","article-title":"The Statistical Modeling and Macro-analysis of Chinese Classical Poetry (\u4e2d\u56fd\u53e4\u8bd7\u7edf\u8ba1\u5efa\u6a21\u4e0e\u5b8f\u89c2\u5206\u6790)\u2019","volume":"39","author":"Qian","year":"2015","journal-title":"Journal of Jiangxi Normal University (Natural Science)"},{"key":"2024040210375490600_fqad073-B27","volume-title":"The Complete Taiwan Poems","author":"Shi","year":"2011"},{"key":"2024040210375490600_fqad073-B28","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1002\/asi.24544","article-title":"Text Analysis Using Deep Neural Networks in Digital Humanities and Information Science\u2019","volume":"73","author":"Suissa","year":"2021","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"2024040210375490600_fqad073-B29","volume-title":"Some Linguistic Analyses of Chinese Literature: Three Studies of Tang and Song Poems (\u5f9e\u8a9e\u8a00\u5b78\u770b\u6587\u5b78\uff1a\u5510\u5b8b\u8fd1\u9ad4\u8a69\u4e09\u8ad6).","author":"Tsao","year":"2004"},{"key":"2024040210375490600_fqad073-B30","volume-title":"The Collection of Wang Li (\u738b\u529b\u5168\u96c6) (reprint)","author":"Wang","year":"1972"},{"key":"2024040210375490600_fqad073-B31","volume-title":"Studies on the Correspondences between Tang Poems and Song Ci (\u5b8b\u8a5e\u8207\u5510\u8a69\u4e4b\u5c0d\u61c9\u95dc\u4fc2).","author":"Wang","year":"2003"},{"key":"2024040210375490600_fqad073-B32","first-page":"631","article-title":"Word-based Statistical Analysis of Chinese Ancient Poetry (\u5510\u5b8b\u8a69\u4e4b\u8a5e\u532f\u81ea\u52d5\u5206\u6790\u53ca\u61c9\u7528)\u2019","volume":"4","author":"Yu","year":"2003","journal-title":"Language and Linguistics"}],"container-title":["Digital Scholarship in the Humanities"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/dsh\/article-pdf\/39\/1\/228\/57134455\/fqad073.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/dsh\/article-pdf\/39\/1\/228\/57134455\/fqad073.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T13:56:11Z","timestamp":1712066171000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/dsh\/article\/39\/1\/228\/7325848"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,20]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,10,20]]},"published-print":{"date-parts":[[2024,4,2]]}},"URL":"https:\/\/doi.org\/10.1093\/llc\/fqad073","relation":{},"ISSN":["2055-7671","2055-768X"],"issn-type":[{"value":"2055-7671","type":"print"},{"value":"2055-768X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,4,1]]},"published":{"date-parts":[[2023,10,20]]}}}