University of Illinois Urbana-Champaign

Bilingual sentence alignment of pre-Qin history literature for digital humanities study

Liang, Jiwen; Wang, Dongbo; Yang, Jianlin

Permalink

https://hdl.handle.net/2142/106595

Description

Title
Bilingual sentence alignment of pre-Qin history literature for digital humanities study
Author(s)
  • Liang, Jiwen
  • Wang, Dongbo
  • Yang, Jianlin
Issue Date
2020-03-23
Keyword(s)
  • Sentence alignment
  • Cross-language information processing
  • Ancient Chinese and English parallel corpus
  • History literature
Abstract
Sentence aligned bilingual text of history literature provides support of digital resources for related digital humanities studies, but existing studies have done little work on sentence alignment of ancient Chinese and English. In this study, we made a preliminary attempt to align the sentence of ancient Chinese and English. We used the bilingual text of the Analects of Confucius and Zuo's Commentaries of the Spring and Autumn Annals, extracted features and adopted the classification method to divide the bilingual candidate sentence pairs based on probability scores. The bilingual sentence alignment model based on SVM had the best performance on a larger amount of data when using three features and confirmed the impact of candidate dataset.
Publisher
iSchools
Series/Report Name or Number
iConference 2020 Proceedings
Type of Resource
text
Language
eng
Permalink
http://hdl.handle.net/2142/106595
Copyright and License Information
Copyright 2020 Jiwen Liang, Dongbo Wang, and Jianlin Yang

Owning Collections

iConference 2020 Poster Descriptions PRIMARY