Source-language entailment modeling for translating unknown terms

S Mirkin; L Specia; N Cancedda; I Dagan; M Dymetman; I Szpektor

Source-language entailment modeling for translating unknown terms

S Mirkin, L Specia, N Cancedda, I Dagan, M Dymetman, I Szpektor

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper addresses the task of handling unknown terms in SMT. We propose using source-language monolingual models and resources to paraphrase the source text prior to translation. We further present a conceptual extension to prior work by allowing translations of entailed texts rather than paraphrases only. A method for performing this process efficiently is presented and applied to some 2500 sentences with unknown terms. Our experiments show that the proposed approach substantially increases the number of properly translated texts.

Original language	American English
Title of host publication	The Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP
Publisher	Association for Computational Linguistics
State	Published - 2009

Bibliographical note

Place of conference:Suntec, Singapore

Cite this

@inproceedings{c3bc4d0c3d064a18b3bb6eeaf1317ff6,

title = "Source-language entailment modeling for translating unknown terms",

abstract = "This paper addresses the task of handling unknown terms in SMT. We propose using source-language monolingual models and resources to paraphrase the source text prior to translation. We further present a conceptual extension to prior work by allowing translations of entailed texts rather than paraphrases only. A method for performing this process efficiently is presented and applied to some 2500 sentences with unknown terms. Our experiments show that the proposed approach substantially increases the number of properly translated texts.",

author = "S Mirkin and L Specia and N Cancedda and I Dagan and M Dymetman and I Szpektor",

note = "Place of conference:Suntec, Singapore",

year = "2009",

language = "American English",

booktitle = "The Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP",

publisher = "Association for Computational Linguistics",

}

Source-language entailment modeling for translating unknown terms. / Mirkin, S; Specia, L; Cancedda, N et al.
The Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Association for Computational Linguistics, 2009.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Source-language entailment modeling for translating unknown terms

AU - Mirkin, S

AU - Specia, L

AU - Cancedda, N

AU - Dagan, I

AU - Dymetman, M

AU - Szpektor, I

N1 - Place of conference:Suntec, Singapore

PY - 2009

Y1 - 2009

N2 - This paper addresses the task of handling unknown terms in SMT. We propose using source-language monolingual models and resources to paraphrase the source text prior to translation. We further present a conceptual extension to prior work by allowing translations of entailed texts rather than paraphrases only. A method for performing this process efficiently is presented and applied to some 2500 sentences with unknown terms. Our experiments show that the proposed approach substantially increases the number of properly translated texts.

AB - This paper addresses the task of handling unknown terms in SMT. We propose using source-language monolingual models and resources to paraphrase the source text prior to translation. We further present a conceptual extension to prior work by allowing translations of entailed texts rather than paraphrases only. A method for performing this process efficiently is presented and applied to some 2500 sentences with unknown terms. Our experiments show that the proposed approach substantially increases the number of properly translated texts.

UR - https://scholar.google.co.il/scholar?q=Source-Language+Entailment+Modeling+for+Translating+Unknown+Terms&btnG=&hl=en&as_sdt=0%2C5

M3 - Conference contribution

BT - The Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

PB - Association for Computational Linguistics

ER -

Source-language entailment modeling for translating unknown terms

Abstract

Bibliographical note

Other files and links

Fingerprint

Cite this