1887
Volume 2, Issue 2
  • ISSN 1877-7031
  • E-ISSN: 1877-8798
USD
Buy:$35.00 + Taxes

Abstract

We address the issue of poetic discourse in classical Chinese poetry and propose the use of imageries as characteristic anchors that stylistically differentiate poetic schools as well as individual poets. We describe an experiment that is aimed at the use of ontological knowledge to identify patterns of imagery use as stylistic features of classical Chinese poetry for authorship attribution of classical Chinese poems. This work is motivated by the understanding that the creative language use by different poets can be characterised through their creative use of imageries which can be captured through ontological annotation. A corpus of lyric songs written by Liu Yong and Su Shi in the Song Dynasty is used, which is word segmented and ontologically annotated. State-of-the-art techniques in automatic text classification are adopted and machine learning methods applied to evaluate the performance of the imagery-based features. Empirical results show that word tokens alone can be used to achieve an accuracy of 87% in the task of authorship attribution between Liu Yong and Su Shi. More interestingly, ontological knowledge is shown to produce significant performance gains when combined with word tokens. This observation is reinforced by the fact that most of the feature sets with ontological annotation outperform the use of bare word tokens as features. Our empirical evidence strongly suggests that the use of imageries is a powerful indicator of poetic discourse that is characteristic of the two poets concerned in the study.
Loading

Article metrics loading...

/content/journals/10.1075/cld.2.2.04fan
2011-01-01
2019-10-19
Loading full text...

Full text loading...

References

http://instance.metastore.ingenta.com/content/journals/10.1075/cld.2.2.04fan
Loading
  • Article Type: Research Article
Keyword(s): classical Chinese poetry , corpus , imagery , Liu Yong , poetic discourse , Su Shi and text classification
This is a required field
Please enter a valid email address
Approval was successful
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error