L1-L2 Parallel Dependency Treebank as Learner Corpus

John Lee; Keying Li; Herman Leung

L1-L2 Parallel Dependency Treebank as Learner Corpus

John Lee
, Keying Li
, Herman Leung

Department of Linguistics and Translation

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

6 Citations (Scopus)

Abstract

This opinion paper proposes the use of parallel treebank as learner corpus. We show how an L1-L2 parallel treebank - i.e., parse trees of non-native sentences, aligned to the parse trees of their target hypotheses - can facilitate retrieval of sentences with specific learner errors. We argue for its benefits, in terms of corpus reuse and interoperability, over a conventional learner corpus annotated with error tags. As a proof of concept, we conduct a case study on word-order errors made by learners of Chinese as a foreign language. We report precision and recall in retrieving a range of word-order error categories from L1-L2 tree pairs annotated in the Universal Dependency framework. © 2017 Association for Computational Linguistics

Original language	English
Title of host publication	Proceedings of the 15th International Conference on Parsing Technologies
Editors	Yusuke Miyao, Kenji Sagae
Publisher	Association for Computational Linguistics
Pages	44-49
ISBN (Electronic)	9781945626739
ISBN (Print)	9781945626739
Publication status	Published - Sept 2017
Event	The 15th International Conference on Parsing Technologies (IWPT 2017) - Pisa, Italy Duration: 20 Sept 2017 → 22 Sept 2017 http://compling.ucdavis.edu/iwpt2017/ http://compling.ucdavis.edu/iwpt2017/proceedings/index.html http://compling.ucdavis.edu/iwpt2017/proceedings/IWPT-2017.pdf https://aclanthology.org/W17-63

Publication series

Name	IWPT - International Conference on Parsing Technologies, Proceedings

Conference

Conference	The 15th International Conference on Parsing Technologies (IWPT 2017)
Abbreviated title	IWPT 2017
Place	Italy
City	Pisa
Period	20/09/17 → 22/09/17
Internet address	http://compling.ucdavis.edu/iwpt2017/ http://compling.ucdavis.edu/iwpt2017/proceedings/index.html http://compling.ucdavis.edu/iwpt2017/proceedings/IWPT-2017.pdf https://aclanthology.org/W17-63

Access Output

https://aclanthology.org/W17-6306/

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{6ea0886f0a044805980e38c267fdc576,

title = "L1-L2 Parallel Dependency Treebank as Learner Corpus",

abstract = "This opinion paper proposes the use of parallel treebank as learner corpus. We show how an L1-L2 parallel treebank - i.e., parse trees of non-native sentences, aligned to the parse trees of their target hypotheses - can facilitate retrieval of sentences with specific learner errors. We argue for its benefits, in terms of corpus reuse and interoperability, over a conventional learner corpus annotated with error tags. As a proof of concept, we conduct a case study on word-order errors made by learners of Chinese as a foreign language. We report precision and recall in retrieving a range of word-order error categories from L1-L2 tree pairs annotated in the Universal Dependency framework. {\textcopyright} 2017 Association for Computational Linguistics",

author = "John Lee and Keying Li and Herman Leung",

year = "2017",

month = sep,

language = "English",

isbn = "9781945626739",

series = "IWPT - International Conference on Parsing Technologies, Proceedings",

publisher = "Association for Computational Linguistics",

pages = "44--49",

editor = "Yusuke Miyao and Kenji Sagae",

booktitle = "Proceedings of the 15th International Conference on Parsing Technologies",

address = "United States",

note = "The 15th International Conference on Parsing Technologies (IWPT 2017), IWPT 2017 ; Conference date: 20-09-2017 Through 22-09-2017",

url = "http://compling.ucdavis.edu/iwpt2017/, http://compling.ucdavis.edu/iwpt2017/proceedings/index.html, http://compling.ucdavis.edu/iwpt2017/proceedings/IWPT-2017.pdf, https://aclanthology.org/W17-63",

}

Lee, J , Li, K & Leung, H 2017, L1-L2 Parallel Dependency Treebank as Learner Corpus. in Y Miyao & K Sagae (eds), Proceedings of the 15th International Conference on Parsing Technologies. IWPT - International Conference on Parsing Technologies, Proceedings, Association for Computational Linguistics, pp. 44-49, The 15th International Conference on Parsing Technologies (IWPT 2017), Pisa, Italy, 20/09/17. <https://aclanthology.org/W17-6306/>

L1-L2 Parallel Dependency Treebank as Learner Corpus. / Lee, John ; Li, Keying; Leung, Herman.
Proceedings of the 15th International Conference on Parsing Technologies. ed. / Yusuke Miyao; Kenji Sagae. Association for Computational Linguistics, 2017. p. 44-49 (IWPT - International Conference on Parsing Technologies, Proceedings).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - L1-L2 Parallel Dependency Treebank as Learner Corpus

AU - Lee, John

AU - Li, Keying

AU - Leung, Herman

PY - 2017/9

Y1 - 2017/9

N2 - This opinion paper proposes the use of parallel treebank as learner corpus. We show how an L1-L2 parallel treebank - i.e., parse trees of non-native sentences, aligned to the parse trees of their target hypotheses - can facilitate retrieval of sentences with specific learner errors. We argue for its benefits, in terms of corpus reuse and interoperability, over a conventional learner corpus annotated with error tags. As a proof of concept, we conduct a case study on word-order errors made by learners of Chinese as a foreign language. We report precision and recall in retrieving a range of word-order error categories from L1-L2 tree pairs annotated in the Universal Dependency framework. © 2017 Association for Computational Linguistics

AB - This opinion paper proposes the use of parallel treebank as learner corpus. We show how an L1-L2 parallel treebank - i.e., parse trees of non-native sentences, aligned to the parse trees of their target hypotheses - can facilitate retrieval of sentences with specific learner errors. We argue for its benefits, in terms of corpus reuse and interoperability, over a conventional learner corpus annotated with error tags. As a proof of concept, we conduct a case study on word-order errors made by learners of Chinese as a foreign language. We report precision and recall in retrieving a range of word-order error categories from L1-L2 tree pairs annotated in the Universal Dependency framework. © 2017 Association for Computational Linguistics

UR - https://www.scopus.com/pages/publications/85059916381

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85059916381&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781945626739

T3 - IWPT - International Conference on Parsing Technologies, Proceedings

SP - 44

EP - 49

BT - Proceedings of the 15th International Conference on Parsing Technologies

A2 - Miyao, Yusuke

A2 - Sagae, Kenji

PB - Association for Computational Linguistics

T2 - The 15th International Conference on Parsing Technologies (IWPT 2017)

Y2 - 20 September 2017 through 22 September 2017

ER -

L1-L2 Parallel Dependency Treebank as Learner Corpus

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this