Influence of dependency parsing on the prosody of Chinese discourse

Yu Pang, Yuan Jia, Aijun Li, Dawei Song, Ruifang He

Research output: Contribution to journalConference articlepeer-review

3 Citations (Scopus)

Abstract

Dependency parsing has been a prime focus of Natural Language Processing. The present paper was attempting to elucidate the relationship between prosodic variation and syntactic structure within the framework of dependency parsing. The study adopted Harbin Institute of Technology (HIT) dependency parsing tool to annotate Chinese spoken discourse corpus. Duration variation and stress distribution patterns were employed as parameters to examine the interactions of the syntactic structures and the prosodic features. Preliminary results demonstrated that there was an intrinsic association between duration variation and dependency relation. Specifically, governor duration was more likely to be longer than dependent duration of dependency relations of Left- Adjunct, Mood-Tense, Attribute, Quantity and so on. Moreover, in “DE” Construction, Preposition-Object and Verb-Object, the dependent duration was much longer.

Original languageEnglish
Pages (from-to)380-384
Number of pages5
JournalProceedings of the International Conference on Speech Prosody
Volume2016-January
DOIs
Publication statusPublished - 2016
Externally publishedYes
Event8th Speech Prosody 2016 - Boston, United States
Duration: 31 May 20163 Jun 2016

Keywords

  • Dependency parsing
  • Duration variation
  • Stress Distribution

Fingerprint

Dive into the research topics of 'Influence of dependency parsing on the prosody of Chinese discourse'. Together they form a unique fingerprint.

Cite this