Proceedings of the 17th International Conference on Computational Linguistics - 1998
DOI: 10.3115/980451.980932
|View full text |Cite
|
Sign up to set email alerts
|

Definiteness predictions for Japanese noun phrases

Abstract: One of the major problems when translating from Japanese into a European language such as German or English is to determine definiteness of noun phrases in order to choose the correct determiner in the target language. Even though in Japanese, noun phrase reference is said to depend in large parts on the discourse context, we show that in many cases there also exist linguistic markers for definiteness. We use these to build a rule hierarchy that predicts 79,5% of the articles with an accuracy of 98,9% from syn… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2013
2013
2023
2023

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(5 citation statements)
references
References 4 publications
0
3
0
Order By: Relevance
“…Eeg-Olofsson and Knutsson (2003) report on a rule-based system that detects and corrects preposition errors in Swedish texts produced by nonnative writers. Rule-based approaches have also been used to predict definiteness and indefiniteness of Japanese noun phrases as a preprocessing step for machine translation into English (Murata & Nagao, 1993;Bond, Ogura, & Ikehara, 1994;Heine, 1998), a task that is similar to the prediction of English articles. Data-driven approaches have gained popularity throughout the past decade and have been applied to article prediction in English (Knight & Chander, 1994;Minnen, Bond, & Copestake, 2000;Turner & Charniak, 2007), an array of Japanese learners' errors in English (Izumi, Uchimoto, Saiga, Supnithi, & Isahara, 2003), and article and preposition correction in ESL text (Han, Chodorow, & Leacock, 2004;Nagata, Wakana, Masui, Kawai, & Isu, 2005;Nagata, Kawai, Morihiro, & Isu, 2006;De Felice & Pulman, 2007;Chodorow, Tetreault, & Han, 2007;Tetreault & Chodorow, 2008a;Gamon et al, 2008).…”
Section: Different Solutions For Different Types Of Errorsmentioning
confidence: 99%
“…Eeg-Olofsson and Knutsson (2003) report on a rule-based system that detects and corrects preposition errors in Swedish texts produced by nonnative writers. Rule-based approaches have also been used to predict definiteness and indefiniteness of Japanese noun phrases as a preprocessing step for machine translation into English (Murata & Nagao, 1993;Bond, Ogura, & Ikehara, 1994;Heine, 1998), a task that is similar to the prediction of English articles. Data-driven approaches have gained popularity throughout the past decade and have been applied to article prediction in English (Knight & Chander, 1994;Minnen, Bond, & Copestake, 2000;Turner & Charniak, 2007), an array of Japanese learners' errors in English (Izumi, Uchimoto, Saiga, Supnithi, & Isahara, 2003), and article and preposition correction in ESL text (Han, Chodorow, & Leacock, 2004;Nagata, Wakana, Masui, Kawai, & Isu, 2005;Nagata, Kawai, Morihiro, & Isu, 2006;De Felice & Pulman, 2007;Chodorow, Tetreault, & Han, 2007;Tetreault & Chodorow, 2008a;Gamon et al, 2008).…”
Section: Different Solutions For Different Types Of Errorsmentioning
confidence: 99%
“…Nonetheless, noun phrases can also be marked explicitly for their certainty, thereby forcing the interpretation of their referents to be independent of discourse context. In this way, it is possible to trigger the accommodation of previously unknown specific references or obtain unlimited readings even if objects of the same type have been introduced (Heine, 1998).…”
mentioning
confidence: 99%
“…There are some nouns, which can be marked as definite words based on their lexical nature alone, either because they refer to a unique reference in the world of discourse, or because they carry some sort of indexical implication. Such references are uniquely explained with respect to some of the implicitly mentioned contexts (Heine, 1998).…”
mentioning
confidence: 99%
“…Most of the early researches on article problem have been using rules to improve the quality of text [2,3]. In the research of Japanese and English translation, Heine [3] focused on Japanese NP and classified whether it is definite or indefinite.…”
Section: Il Related Researchmentioning
confidence: 99%
“…In the research of Japanese and English translation, Heine [3] focused on Japanese NP and classified whether it is definite or indefinite. The detection rules were all extracted by hands.…”
Section: Il Related Researchmentioning
confidence: 99%