Natural Language Processing for Digital Humanities: How to Analyze the Related Materials of Traditional Chinese Drama in the Early 20th Century (1900-1937) from the Perspective of Digital Humanities—Focusing on Newspaper Databases, Record Databases, and Script Collections

Chao-Lin Liu; Jen-Joe  Hung; Wan-yi Wu; Su-bing Chang

Natural Language Processing for Digital Humanities: How to Analyze the Related Materials of Traditional Chinese Drama in the Early 20th Century (1900-1937) from the Perspective of Digital Humanities—Focusing on Newspaper Databases, Record Databases, and Script Collections

Chao-Lin Liu, Jen-Joe Hung, Wan-yi Wu, Su-bing Chang

Research output: Unpublished conference presentation (presented paper, abstract, poster) › Conference presentation (not published in journal/proceeding/book) › Academic research › peer-review

Abstract

The research of digital humanities has flourished in the past decade internationally. In contrast,
the participation of researchers of computational linguistics in domestic research projects
remains less common than one may have anticipated. The goal of this panel is to introduce
sample research projects of digital humanities to the community of computational linguistics,
hoping to promote further cooperation between the two communities. The panel consists of
four parts. Hung introduces the online repository of the Taishō Tripiṭaka that the Chinese
Buddhist Electronic Text Association (often called CBETA) offers. Applications of language
technology, including artificial intelligence and natural language processing, for the
construction of CBETA will be discussed. Chang and her colleagues aim to build the Taiwan
Biographical Database (TBDB), which, in the long term, will serve as part of the bedrock for
historical studies about Taiwan. Experience about how the research team extracted and
integrated the information from some collections of local gazetteers to build the TBDB will be
discusses. Dramas are important part of Chinese arts. Relevant materials about dramas are
available in some different databases and in different forms. Wu will share with us her study
on Chinese dramas, and elaborates on the potential contributions of language technology to the
studies of Chinese dramas. If time allows, Liu plans to outline his work on optical character
recognition (OCR) for ancient Chinese documents, sentence segmentation for classical Chinese,
word segmentation for classical Chinese poems, including the Tang and Song poems, and
information extraction from historical documents in classical Chinese.
The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)
Taipei, Taiwan, September 24–26, 2020. The Association for Computational Linguistics and Chinese Language Processing
414

Original language	English
Pages	413-422
Number of pages	500
Publication status	Published - 24 Sept 2020
Event	The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020) - National Taipei University of Technology, Taipei, Taiwan Duration: 24 Sept 2020 → 26 Sept 2023 https://sites.google.com/ntut.org.tw/rocling2020

Conference

Conference	The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)
Country/Territory	Taiwan
City	Taipei
Period	24/09/20 → 26/09/23
Internet address	https://sites.google.com/ntut.org.tw/rocling2020

Fingerprint

Dive into the research topics of 'Natural Language Processing for Digital Humanities: How to Analyze the Related Materials of Traditional Chinese Drama in the Early 20th Century (1900-1937) from the Perspective of Digital Humanities—Focusing on Newspaper Databases, Record Databases, and Script Collections'. Together they form a unique fingerprint.

Cite this

Liu, C.-L., Hung, J.-J., Wu, W., & Chang, S. (2020). Natural Language Processing for Digital Humanities: How to Analyze the Related Materials of Traditional Chinese Drama in the Early 20th Century (1900-1937) from the Perspective of Digital Humanities—Focusing on Newspaper Databases, Record Databases, and Script Collections. 413-422. Paper presented at The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)
, Taipei, Taiwan.

Liu, Chao-Lin ; Hung, Jen-Joe ; Wu, Wan-yi et al. / Natural Language Processing for Digital Humanities : How to Analyze the Related Materials of Traditional Chinese Drama in the Early 20th Century (1900-1937) from the Perspective of Digital Humanities—Focusing on Newspaper Databases, Record Databases, and Script Collections. Paper presented at The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)
, Taipei, Taiwan.500 p.

@conference{7d9942b0ab3344d7a8a3b74decbf45a8,

title = "Natural Language Processing for Digital Humanities: How to Analyze the Related Materials of Traditional Chinese Drama in the Early 20th Century (1900-1937) from the Perspective of Digital Humanities—Focusing on Newspaper Databases, Record Databases, and Script Collections",

abstract = "The research of digital humanities has flourished in the past decade internationally. In contrast,the participation of researchers of computational linguistics in domestic research projectsremains less common than one may have anticipated. The goal of this panel is to introducesample research projects of digital humanities to the community of computational linguistics,hoping to promote further cooperation between the two communities. The panel consists offour parts. Hung introduces the online repository of the Taishō Tripiṭaka that the ChineseBuddhist Electronic Text Association (often called CBETA) offers. Applications of languagetechnology, including artificial intelligence and natural language processing, for theconstruction of CBETA will be discussed. Chang and her colleagues aim to build the TaiwanBiographical Database (TBDB), which, in the long term, will serve as part of the bedrock forhistorical studies about Taiwan. Experience about how the research team extracted andintegrated the information from some collections of local gazetteers to build the TBDB will bediscusses. Dramas are important part of Chinese arts. Relevant materials about dramas areavailable in some different databases and in different forms. Wu will share with us her studyon Chinese dramas, and elaborates on the potential contributions of language technology to thestudies of Chinese dramas. If time allows, Liu plans to outline his work on optical characterrecognition (OCR) for ancient Chinese documents, sentence segmentation for classical Chinese,word segmentation for classical Chinese poems, including the Tang and Song poems, andinformation extraction from historical documents in classical Chinese.The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)Taipei, Taiwan, September 24–26, 2020. The Association for Computational Linguistics and Chinese Language Processing414",

author = "Chao-Lin Liu and Jen-Joe Hung and Wan-yi Wu and Su-bing Chang",

year = "2020",

month = sep,

day = "24",

language = "English",

pages = "413--422",

note = "The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)<br/> ; Conference date: 24-09-2020 Through 26-09-2023",

url = "https://sites.google.com/ntut.org.tw/rocling2020",

}

Liu, C-L, Hung, J-J, Wu, W & Chang, S 2020, 'Natural Language Processing for Digital Humanities: How to Analyze the Related Materials of Traditional Chinese Drama in the Early 20th Century (1900-1937) from the Perspective of Digital Humanities—Focusing on Newspaper Databases, Record Databases, and Script Collections', Paper presented at The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)
, Taipei, Taiwan, 24/09/20 - 26/09/23 pp. 413-422.

Natural Language Processing for Digital Humanities: How to Analyze the Related Materials of Traditional Chinese Drama in the Early 20th Century (1900-1937) from the Perspective of Digital Humanities—Focusing on Newspaper Databases, Record Databases, and Script Collections. / Liu, Chao-Lin; Hung, Jen-Joe; Wu, Wan-yi et al.
2020. 413-422 Paper presented at The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)
, Taipei, Taiwan.

Research output: Unpublished conference presentation (presented paper, abstract, poster) › Conference presentation (not published in journal/proceeding/book) › Academic research › peer-review

TY - CONF

T1 - Natural Language Processing for Digital Humanities

T2 - The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)<br/>

AU - Liu, Chao-Lin

AU - Hung, Jen-Joe

AU - Wu, Wan-yi

AU - Chang, Su-bing

PY - 2020/9/24

Y1 - 2020/9/24

N2 - The research of digital humanities has flourished in the past decade internationally. In contrast,the participation of researchers of computational linguistics in domestic research projectsremains less common than one may have anticipated. The goal of this panel is to introducesample research projects of digital humanities to the community of computational linguistics,hoping to promote further cooperation between the two communities. The panel consists offour parts. Hung introduces the online repository of the Taishō Tripiṭaka that the ChineseBuddhist Electronic Text Association (often called CBETA) offers. Applications of languagetechnology, including artificial intelligence and natural language processing, for theconstruction of CBETA will be discussed. Chang and her colleagues aim to build the TaiwanBiographical Database (TBDB), which, in the long term, will serve as part of the bedrock forhistorical studies about Taiwan. Experience about how the research team extracted andintegrated the information from some collections of local gazetteers to build the TBDB will bediscusses. Dramas are important part of Chinese arts. Relevant materials about dramas areavailable in some different databases and in different forms. Wu will share with us her studyon Chinese dramas, and elaborates on the potential contributions of language technology to thestudies of Chinese dramas. If time allows, Liu plans to outline his work on optical characterrecognition (OCR) for ancient Chinese documents, sentence segmentation for classical Chinese,word segmentation for classical Chinese poems, including the Tang and Song poems, andinformation extraction from historical documents in classical Chinese.The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)Taipei, Taiwan, September 24–26, 2020. The Association for Computational Linguistics and Chinese Language Processing414

AB - The research of digital humanities has flourished in the past decade internationally. In contrast,the participation of researchers of computational linguistics in domestic research projectsremains less common than one may have anticipated. The goal of this panel is to introducesample research projects of digital humanities to the community of computational linguistics,hoping to promote further cooperation between the two communities. The panel consists offour parts. Hung introduces the online repository of the Taishō Tripiṭaka that the ChineseBuddhist Electronic Text Association (often called CBETA) offers. Applications of languagetechnology, including artificial intelligence and natural language processing, for theconstruction of CBETA will be discussed. Chang and her colleagues aim to build the TaiwanBiographical Database (TBDB), which, in the long term, will serve as part of the bedrock forhistorical studies about Taiwan. Experience about how the research team extracted andintegrated the information from some collections of local gazetteers to build the TBDB will bediscusses. Dramas are important part of Chinese arts. Relevant materials about dramas areavailable in some different databases and in different forms. Wu will share with us her studyon Chinese dramas, and elaborates on the potential contributions of language technology to thestudies of Chinese dramas. If time allows, Liu plans to outline his work on optical characterrecognition (OCR) for ancient Chinese documents, sentence segmentation for classical Chinese,word segmentation for classical Chinese poems, including the Tang and Song poems, andinformation extraction from historical documents in classical Chinese.The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)Taipei, Taiwan, September 24–26, 2020. The Association for Computational Linguistics and Chinese Language Processing414

M3 - Conference presentation (not published in journal/proceeding/book)

SP - 413

EP - 422

Y2 - 24 September 2020 through 26 September 2023

ER -

Liu CL, Hung JJ, Wu W, Chang S. Natural Language Processing for Digital Humanities: How to Analyze the Related Materials of Traditional Chinese Drama in the Early 20th Century (1900-1937) from the Perspective of Digital Humanities—Focusing on Newspaper Databases, Record Databases, and Script Collections. 2020. Paper presented at The 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)
, Taipei, Taiwan.