Translation of unseen bigrams by analogy using an SVM classifier

Hao Wang; Lu Lyu; Yves Lepage

Translation of unseen bigrams by analogy using an SVM classifier

Hao Wang, Lu Lyu, Yves Lepage

Graduate School of Information, Production and Systems

Research output: Contribution to conference › Paper › peer-review

Abstract

Detecting language divergences and predicting possible sub-translations is one of the most essential issues in machine translation. Since the existence of translation divergences, it is impractical to straightforward translate from source sentence into target sentence while keeping the high degree of accuracy and without additional information. In this paper, we investigate the problem from an emerging and special point of view: bigrams and the corresponding translations. We first profile corpora and explore the constituents of bigrams in the source language. Then we translate unseen bigrams based on proportional analogy and filter the outputs using an Support Vector Machine (SVM) classifier. The experiment results also show that even a small set of features from analogous can provide meaningful information in translating by analogy.

Original language	English
Pages	16-25
Number of pages	10
Publication status	Published - 2015
Event	29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015 - Shanghai, China Duration: 2015 Oct 30 → 2015 Nov 1

Other

Other	29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015
Country/Territory	China
City	Shanghai
Period	15/10/30 → 15/11/1

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction
Linguistics and Language

Cite this

@conference{906d42e874494a4fb84878bc216d96e7,

title = "Translation of unseen bigrams by analogy using an SVM classifier",

abstract = "Detecting language divergences and predicting possible sub-translations is one of the most essential issues in machine translation. Since the existence of translation divergences, it is impractical to straightforward translate from source sentence into target sentence while keeping the high degree of accuracy and without additional information. In this paper, we investigate the problem from an emerging and special point of view: bigrams and the corresponding translations. We first profile corpora and explore the constituents of bigrams in the source language. Then we translate unseen bigrams based on proportional analogy and filter the outputs using an Support Vector Machine (SVM) classifier. The experiment results also show that even a small set of features from analogous can provide meaningful information in translating by analogy.",

author = "Hao Wang and Lu Lyu and Yves Lepage",

note = "Funding Information: This work is supported in part by China Scholarship Council (CSC) under the CSC Grant No.201406890026 is acknowledged.; 29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015 ; Conference date: 30-10-2015 Through 01-11-2015",

year = "2015",

language = "English",

pages = "16--25",

}

TY - CONF

T1 - Translation of unseen bigrams by analogy using an SVM classifier

AU - Wang, Hao

AU - Lyu, Lu

AU - Lepage, Yves

N1 - Funding Information: This work is supported in part by China Scholarship Council (CSC) under the CSC Grant No.201406890026 is acknowledged.

PY - 2015

Y1 - 2015

N2 - Detecting language divergences and predicting possible sub-translations is one of the most essential issues in machine translation. Since the existence of translation divergences, it is impractical to straightforward translate from source sentence into target sentence while keeping the high degree of accuracy and without additional information. In this paper, we investigate the problem from an emerging and special point of view: bigrams and the corresponding translations. We first profile corpora and explore the constituents of bigrams in the source language. Then we translate unseen bigrams based on proportional analogy and filter the outputs using an Support Vector Machine (SVM) classifier. The experiment results also show that even a small set of features from analogous can provide meaningful information in translating by analogy.

AB - Detecting language divergences and predicting possible sub-translations is one of the most essential issues in machine translation. Since the existence of translation divergences, it is impractical to straightforward translate from source sentence into target sentence while keeping the high degree of accuracy and without additional information. In this paper, we investigate the problem from an emerging and special point of view: bigrams and the corresponding translations. We first profile corpora and explore the constituents of bigrams in the source language. Then we translate unseen bigrams based on proportional analogy and filter the outputs using an Support Vector Machine (SVM) classifier. The experiment results also show that even a small set of features from analogous can provide meaningful information in translating by analogy.

UR - http://www.scopus.com/inward/record.url?scp=84967184852&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84967184852&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84967184852

SP - 16

EP - 25

T2 - 29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015

Y2 - 30 October 2015 through 1 November 2015

ER -

Translation of unseen bigrams by analogy using an SVM classifier

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this