The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo descreve um método para reconhecer palavras japonesas romanizadas no aluno de inglês. Elas se tornam barulhentas e problemáticas em uma variedade de sistemas e ferramentas para aprendizagem e ensino de línguas, incluindo análise de texto, verificação ortográfica e detecção de erros gramaticais, porque são palavras japonesas e, portanto, em sua maioria desconhecidas para tais sistemas e ferramentas. Um problema que encontramos ao reconhecer palavras japonesas romanizadas no inglês do aluno é que as regras de ortografia das palavras japonesas romanizadas são frequentemente violadas. Para resolver este problema, o método descrito utiliza um algoritmo de agrupamento reforçado por um pequeno conjunto de regras. Experimentos mostram que ele atinge um F-medida de 0.879 e supera outros métodos. Eles também mostram que requer apenas o texto alvo e uma lista de palavras em inglês de tamanho razoável.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Ryo NAGATA, Jun-ichi KAKEGAWA, Hiromi SUGIMOTO, Yukiko YABUTA, "A Method for Recognizing Noisy Romanized Japanese Words in Learner English" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 10, pp. 2458-2466, October 2008, doi: 10.1093/ietisy/e91-d.10.2458.
Abstract: This paper describes a method for recognizing romanized Japanese words in learner English. They become noise and problematic in a variety of systems and tools for language learning and teaching including text analysis, spell checking, and grammatical error detection because they are Japanese words and thus mostly unknown to such systems and tools. A problem one encounters when recognizing romanized Japanese words in learner English is that the spelling rules of romanized Japanese words are often violated. To address this problem, the described method uses a clustering algorithm reinforced by a small set of rules. Experiments show that it achieves an F-measure of 0.879 and outperforms other methods. They also show that it only requires the target text and an English word list of reasonable size.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.10.2458/_p
Copiar
@ARTICLE{e91-d_10_2458,
author={Ryo NAGATA, Jun-ichi KAKEGAWA, Hiromi SUGIMOTO, Yukiko YABUTA, },
journal={IEICE TRANSACTIONS on Information},
title={A Method for Recognizing Noisy Romanized Japanese Words in Learner English},
year={2008},
volume={E91-D},
number={10},
pages={2458-2466},
abstract={This paper describes a method for recognizing romanized Japanese words in learner English. They become noise and problematic in a variety of systems and tools for language learning and teaching including text analysis, spell checking, and grammatical error detection because they are Japanese words and thus mostly unknown to such systems and tools. A problem one encounters when recognizing romanized Japanese words in learner English is that the spelling rules of romanized Japanese words are often violated. To address this problem, the described method uses a clustering algorithm reinforced by a small set of rules. Experiments show that it achieves an F-measure of 0.879 and outperforms other methods. They also show that it only requires the target text and an English word list of reasonable size.},
keywords={},
doi={10.1093/ietisy/e91-d.10.2458},
ISSN={1745-1361},
month={October},}
Copiar
TY - JOUR
TI - A Method for Recognizing Noisy Romanized Japanese Words in Learner English
T2 - IEICE TRANSACTIONS on Information
SP - 2458
EP - 2466
AU - Ryo NAGATA
AU - Jun-ichi KAKEGAWA
AU - Hiromi SUGIMOTO
AU - Yukiko YABUTA
PY - 2008
DO - 10.1093/ietisy/e91-d.10.2458
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2008
AB - This paper describes a method for recognizing romanized Japanese words in learner English. They become noise and problematic in a variety of systems and tools for language learning and teaching including text analysis, spell checking, and grammatical error detection because they are Japanese words and thus mostly unknown to such systems and tools. A problem one encounters when recognizing romanized Japanese words in learner English is that the spelling rules of romanized Japanese words are often violated. To address this problem, the described method uses a clustering algorithm reinforced by a small set of rules. Experiments show that it achieves an F-measure of 0.879 and outperforms other methods. They also show that it only requires the target text and an English word list of reasonable size.
ER -