Discourse Tree Structure and Dependency Distance in EFL Writing
Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 32_Refereed conference paper (with ISBN/ISSN) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 20th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2021) |
| Editors | Daniel Dakota, Kilian Evang, Sandra Kübler |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 105–115 |
| ISBN (Print) | 9781955917162 |
| Publication status | Published - Dec 2021 |
Publication series
| Name | TLT - International Workshop on Treebanks and Linguistic Theories, Proceedings - To be held as part of SyntaxFest |
|---|
Conference
| Title | 20th International Workshop on Treebanks and Linguistic Theories (TLT 2021) |
|---|---|
| Location | Online |
| Place | Bulgaria |
| City | Sofia |
| Period | 21 - 25 March 2022 |
Link(s)
| Attachment(s) | Documents
Publisher's Copyright Statement
|
|---|---|
| Document Link | Links
|
| Link to Scopus | https://www.scopus.com/record/display.uri?eid=2-s2.0-85129852108&origin=recordpage |
| Permanent Link | https://scholars.cityu.edu.hk/en/publications/publication(8cb8c674-5a09-49b8-b01d-e302a7b66e81).html |
Abstract
Quantitative research on learner writing has traditionally focused on lexical and syntactic features, but there has been increasing interest in incorporating discourse-level properties. This paper evaluates discourse complexity measures on learner texts in the framework of Rhetorical
Structure Theory (RST). Specifically, we investigate whether discourse dependency distance and embedded structures in RST trees are correlated to learner proficiency level. In an analysis of manually annotated English essays, we found that more proficient learners tend to use longer dependency distance and more embedded structures. Further, an evaluation based on automatic discourse parsing suggests that dependency distance can potentially contribute to automatic assessment of learner texts.
Structure Theory (RST). Specifically, we investigate whether discourse dependency distance and embedded structures in RST trees are correlated to learner proficiency level. In an analysis of manually annotated English essays, we found that more proficient learners tend to use longer dependency distance and more embedded structures. Further, an evaluation based on automatic discourse parsing suggests that dependency distance can potentially contribute to automatic assessment of learner texts.
Research Area(s)
Citation Format(s)
Discourse Tree Structure and Dependency Distance in EFL Writing. / Yuan, Jingting; Lin, Qiuhan; Lee, John S. Y.
Proceedings of the 20th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2021). ed. / Daniel Dakota; Kilian Evang; Sandra Kübler. Association for Computational Linguistics (ACL), 2021. p. 105–115 (TLT - International Workshop on Treebanks and Linguistic Theories, Proceedings - To be held as part of SyntaxFest).Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 32_Refereed conference paper (with ISBN/ISSN) › peer-review
Download Statistics
No data available
