Presentation 2011-10-10
A Rule-based Method of Text Normalization for Casual English
Eleanor CLARK, Kenji ARAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This research introduces an experimental system for the automated normalization of casual, irregularly-formed English used in communications such as Twitter. Our rule-based approach aims to avoid problems caused by user creativity and individuality of language when Twitter-style text is used as input in Machine Translation, and to aid comprehension for non-native speakers of English. We describe the results of two evaluation experiments using our system. Finally, we explore how to effectively utilize the same rule-based approach to generate casual English ; in other words, automatically producing humanlike creative sentences as an AI task.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Natural Language Processing / Text Normalization / Noisy Text / Twitter / Machine Translation
Paper # TL2011-27,NLC2011-24
Date of Issue

Conference Information
Committee NLC
Conference Date 2011/10/3(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Rule-based Method of Text Normalization for Casual English
Sub Title (in English)
Keyword(1) Natural Language Processing
Keyword(2) Text Normalization
Keyword(3) Noisy Text
Keyword(4) Twitter
Keyword(5) Machine Translation
1st Author's Name Eleanor CLARK
1st Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University()
2nd Author's Name Kenji ARAKI
2nd Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
Date 2011-10-10
Paper # TL2011-27,NLC2011-24
Volume (vol) vol.111
Number (no) 228
Page pp.pp.-
#Pages 6
Date of Issue