Verb tense generation

John Lee

doi:10.1016/j.sbspro.2011.10.590

Verb tense generation

John Lee

The Halliday Centre for Intelligent Applications of Language Studies

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

6 Citations (Scopus)

32 Downloads (CityUHK Scholars)

Abstract

Correct usage of verb tenses is important because they encode the temporal order of events in a text. However, tense systems vary from one language to another, and are difficult to master for machines and non-native speakers alike. We present a method to predict verb tenses based on syntactic and lexical features, as well as temporal expressions in the context. A statistical model trained on Conditional Random Fields significantly outperforms the baseline. This model may be used in post-editing verbs in machine translation output and texts written by non-native speakers.

Original language	English
Pages (from-to)	122-130
Journal	Procedia - Social and Behavioral Sciences
Volume	27
DOIs	https://doi.org/10.1016/j.sbspro.2011.10.590
Publication status	Published - 2011
Event	Conference on Pacific Association for Computational Linguistics, PACLING 2011 - Kuala Lumpur, Malaysia Duration: 19 Jul 2011 → 21 Jul 2011

Research Keywords

separated by semicolons
Type your keywords here

Publisher's Copyright Statement

This full text is made available under CC-BY-NC-ND 3.0. https://creativecommons.org/licenses/by-nc-nd/3.0/

Access Output

10.1016/j.sbspro.2011.10.590

5721307.pdfFinal Published version, 307 KBLicence: CC BY-NC-ND

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{fb6aa730a7de4367a3092160f3401aca,

title = "Verb tense generation",

abstract = "Correct usage of verb tenses is important because they encode the temporal order of events in a text. However, tense systems vary from one language to another, and are difficult to master for machines and non-native speakers alike. We present a method to predict verb tenses based on syntactic and lexical features, as well as temporal expressions in the context. A statistical model trained on Conditional Random Fields significantly outperforms the baseline. This model may be used in post-editing verbs in machine translation output and texts written by non-native speakers.",

keywords = "separated by semicolons, Type your keywords here",

author = "John Lee",

year = "2011",

doi = "10.1016/j.sbspro.2011.10.590",

language = "English",

volume = "27",

pages = "122--130",

journal = "Procedia - Social and Behavioral Sciences",

issn = "1877-0428",

publisher = "Elsevier B.V.",

note = "Conference on Pacific Association for Computational Linguistics, PACLING 2011 ; Conference date: 19-07-2011 Through 21-07-2011",

}

TY - JOUR

T1 - Verb tense generation

AU - Lee, John

PY - 2011

Y1 - 2011

N2 - Correct usage of verb tenses is important because they encode the temporal order of events in a text. However, tense systems vary from one language to another, and are difficult to master for machines and non-native speakers alike. We present a method to predict verb tenses based on syntactic and lexical features, as well as temporal expressions in the context. A statistical model trained on Conditional Random Fields significantly outperforms the baseline. This model may be used in post-editing verbs in machine translation output and texts written by non-native speakers.

AB - Correct usage of verb tenses is important because they encode the temporal order of events in a text. However, tense systems vary from one language to another, and are difficult to master for machines and non-native speakers alike. We present a method to predict verb tenses based on syntactic and lexical features, as well as temporal expressions in the context. A statistical model trained on Conditional Random Fields significantly outperforms the baseline. This model may be used in post-editing verbs in machine translation output and texts written by non-native speakers.

KW - separated by semicolons

KW - Type your keywords here

UR - http://www.scopus.com/inward/record.url?scp=83755181564&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-83755181564&origin=recordpage

U2 - 10.1016/j.sbspro.2011.10.590

DO - 10.1016/j.sbspro.2011.10.590

M3 - RGC 21 - Publication in refereed journal

SN - 1877-0428

VL - 27

SP - 122

EP - 130

JO - Procedia - Social and Behavioral Sciences

JF - Procedia - Social and Behavioral Sciences

T2 - Conference on Pacific Association for Computational Linguistics, PACLING 2011

Y2 - 19 July 2011 through 21 July 2011

ER -

Verb tense generation

Abstract

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this