Extrinsic evaluation of sentence alignment systems

Sadaf Abdul-Rauf; Mark Fishel; Patrik Lambert; Sandra Noubours; Rico Sennrich

Extrinsic evaluation of sentence alignment systems

Sadaf Abdul-Rauf, Mark Fishel, Patrik Lambert, Sandra Noubours, Rico Sennrich

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

Abstract

Parallel corpora are usually a collection of documents which are translations of each other. To be useful in NLP applications such as word alignment or machine translation, they first have to be aligned at the sentence level. This paper is a user study briefly reviewing several sentence aligners and evaluating them based on the performance achieved by the SMT systems trained on their output. We conducted experiments on two language pairs and showed that using a more advanced sentence alignment algorithm may yield gains of 0.5 to 1 BLEU points.

Original language	English
Title of host publication	Workshop on Creating Cross-language Resources for Disconnected Languages and Styles
Pages	6-10
Number of pages	5
Publication status	Published - 1 May 2012
Event	Workshop on Creating Cross-language Resources for Disconnected Languages and Styles - Istanbul, Turkey Duration: 27 May 2012 → 27 May 2012

Workshop

Workshop	Workshop on Creating Cross-language Resources for Disconnected Languages and Styles
Country/Territory	Turkey
City	Istanbul
Period	27/05/12 → 27/05/12

Access to Document

Extrinsic evaluation of sentence alignment systemsFinal published version, 112 KB

http://dx.doi.org/10.5167/uzh-62565

Cite this

@inproceedings{eb737b47138842bdbc5f0d86df359374,

title = "Extrinsic evaluation of sentence alignment systems",

abstract = "Parallel corpora are usually a collection of documents which are translations of each other. To be useful in NLP applications such as word alignment or machine translation, they first have to be aligned at the sentence level. This paper is a user study briefly reviewing several sentence aligners and evaluating them based on the performance achieved by the SMT systems trained on their output. We conducted experiments on two language pairs and showed that using a more advanced sentence alignment algorithm may yield gains of 0.5 to 1 BLEU points.",

author = "Sadaf Abdul-Rauf and Mark Fishel and Patrik Lambert and Sandra Noubours and Rico Sennrich",

year = "2012",

month = may,

day = "1",

language = "English",

pages = "6--10",

booktitle = "Workshop on Creating Cross-language Resources for Disconnected Languages and Styles",

note = "Workshop on Creating Cross-language Resources for Disconnected Languages and Styles ; Conference date: 27-05-2012 Through 27-05-2012",

}

Abdul-Rauf, S, Fishel, M, Lambert, P, Noubours, S & Sennrich, R 2012, Extrinsic evaluation of sentence alignment systems. in Workshop on Creating Cross-language Resources for Disconnected Languages and Styles. pp. 6-10, Workshop on Creating Cross-language Resources for Disconnected Languages and Styles, Istanbul, Turkey, 27/05/12. <http://dx.doi.org/10.5167/uzh-62565>

TY - GEN

T1 - Extrinsic evaluation of sentence alignment systems

AU - Abdul-Rauf, Sadaf

AU - Fishel, Mark

AU - Lambert, Patrik

AU - Noubours, Sandra

AU - Sennrich, Rico

PY - 2012/5/1

Y1 - 2012/5/1

N2 - Parallel corpora are usually a collection of documents which are translations of each other. To be useful in NLP applications such as word alignment or machine translation, they first have to be aligned at the sentence level. This paper is a user study briefly reviewing several sentence aligners and evaluating them based on the performance achieved by the SMT systems trained on their output. We conducted experiments on two language pairs and showed that using a more advanced sentence alignment algorithm may yield gains of 0.5 to 1 BLEU points.

AB - Parallel corpora are usually a collection of documents which are translations of each other. To be useful in NLP applications such as word alignment or machine translation, they first have to be aligned at the sentence level. This paper is a user study briefly reviewing several sentence aligners and evaluating them based on the performance achieved by the SMT systems trained on their output. We conducted experiments on two language pairs and showed that using a more advanced sentence alignment algorithm may yield gains of 0.5 to 1 BLEU points.

M3 - Conference contribution

SP - 6

EP - 10

BT - Workshop on Creating Cross-language Resources for Disconnected Languages and Styles

T2 - Workshop on Creating Cross-language Resources for Disconnected Languages and Styles

Y2 - 27 May 2012 through 27 May 2012

ER -

Extrinsic evaluation of sentence alignment systems

Abstract

Workshop

Access to Document

Fingerprint

Cite this