Automatic article restoration

John Lee

doi:10.3115/1614038.1614044

Automatic article restoration

^*Corresponding author for this work

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

27 Citations (Scopus)

Abstract

One common mistake made by non-native speakers of English is to drop the articles a, an, or the. We apply the log-linear model to automatically restore missing articles based on features of the noun phrase. We first show that the model yields competitive results in article generation. Further, we describe methods to adjust the model with respect to the initial quality of the sentence. Our best results are 20.5% article error rate (insertions, deletions and substitutions) for sentences where 30% of the articles have been dropped, and 38.5% for those where 70% of the articles have been dropped.

Original language	English
Title of host publication	HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop
Publisher	Association for Computational Linguistics
Pages	31-36
DOIs	https://doi.org/10.3115/1614038.1614044
Publication status	Published - 2004
Externally published	Yes
Event	2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics - Student Research Workshop, HLT-NAACL 2004 - Boston, United States Duration: 2 May 2004 → 7 May 2004 https://aclanthology.org/N04-2000/

Publication series

Name	HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop

Conference

Conference	2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics - Student Research Workshop, HLT-NAACL 2004
Country/Territory	United States
City	Boston
Period	2/05/04 → 7/05/04
Internet address	https://aclanthology.org/N04-2000/

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Access Output

10.3115/1614038.1614044

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Lee, J. (2004). Automatic article restoration. In HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop (pp. 31-36). (HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop). Association for Computational Linguistics. https://doi.org/10.3115/1614038.1614044

Lee, John. / Automatic article restoration. HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop. Association for Computational Linguistics, 2004. pp. 31-36 (HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop).

@inproceedings{9cf408e8e875431eb193a05a1f49b1f3,

title = "Automatic article restoration",

abstract = "One common mistake made by non-native speakers of English is to drop the articles a, an, or the. We apply the log-linear model to automatically restore missing articles based on features of the noun phrase. We first show that the model yields competitive results in article generation. Further, we describe methods to adjust the model with respect to the initial quality of the sentence. Our best results are 20.5% article error rate (insertions, deletions and substitutions) for sentences where 30% of the articles have been dropped, and 38.5% for those where 70% of the articles have been dropped.",

author = "John Lee",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; 2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics - Student Research Workshop, HLT-NAACL 2004 ; Conference date: 02-05-2004 Through 07-05-2004",

year = "2004",

doi = "10.3115/1614038.1614044",

language = "English",

series = "HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop",

publisher = "Association for Computational Linguistics",

pages = "31--36",

booktitle = "HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop",

address = "United States",

url = "https://aclanthology.org/N04-2000/",

}

Lee, J 2004, Automatic article restoration. in HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop. HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop, Association for Computational Linguistics, pp. 31-36, 2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics - Student Research Workshop, HLT-NAACL 2004, Boston, United States, 2/05/04. https://doi.org/10.3115/1614038.1614044

Automatic article restoration. / Lee, John.
HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop. Association for Computational Linguistics, 2004. p. 31-36 (HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop).

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

TY - GEN

T1 - Automatic article restoration

AU - Lee, John

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2004

Y1 - 2004

N2 - One common mistake made by non-native speakers of English is to drop the articles a, an, or the. We apply the log-linear model to automatically restore missing articles based on features of the noun phrase. We first show that the model yields competitive results in article generation. Further, we describe methods to adjust the model with respect to the initial quality of the sentence. Our best results are 20.5% article error rate (insertions, deletions and substitutions) for sentences where 30% of the articles have been dropped, and 38.5% for those where 70% of the articles have been dropped.

AB - One common mistake made by non-native speakers of English is to drop the articles a, an, or the. We apply the log-linear model to automatically restore missing articles based on features of the noun phrase. We first show that the model yields competitive results in article generation. Further, we describe methods to adjust the model with respect to the initial quality of the sentence. Our best results are 20.5% article error rate (insertions, deletions and substitutions) for sentences where 30% of the articles have been dropped, and 38.5% for those where 70% of the articles have been dropped.

UR - http://www.scopus.com/inward/record.url?scp=67649563910&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-67649563910&origin=recordpage

U2 - 10.3115/1614038.1614044

DO - 10.3115/1614038.1614044

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

T3 - HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop

SP - 31

EP - 36

BT - HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop

PB - Association for Computational Linguistics

T2 - 2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics - Student Research Workshop, HLT-NAACL 2004

Y2 - 2 May 2004 through 7 May 2004

ER -

Lee J. Automatic article restoration. In HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop. Association for Computational Linguistics. 2004. p. 31-36. (HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop). doi: 10.3115/1614038.1614044

Automatic article restoration

Abstract

Publication series

Conference

Bibliographical note

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this