BEER 1.1: ILLC UvA submission to metrics and tuning task

Milos Stanojevic; Khalil Sima'an

doi:10.18653/v1/W15-3050

BEER 1.1: ILLC UvA submission to metrics and tuning task

Milos Stanojevic, Khalil Sima'an

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

Abstract / Description of output

We describe the submissions of ILLC UvA to the metrics and tuning tasks on WMT15. Both submissions are based on the BEER evaluation metric originally presented on WMT14 (Stanojevic´ and Sima’an, 2014a). The main changes introduced this year are: (i) extending the learning-to-rank trained sentence level metric to the corpus level (but still decomposable to sentence level), (ii) incorporating syntactic ingredients based on dependency trees, and (iii) a technique for finding parameters of BEER that avoid “gaming of the metric” during tuning.

Original language	English
Title of host publication	Proceedings of the Tenth Workshop on Statistical Machine Translation
Place of Publication	Lisboa, Portugal
Publisher	Association for Computational Linguistics (ACL)
Pages	396-401
Number of pages	6
DOIs	https://doi.org/10.18653/v1/W15-3050
Publication status	Published - Sept 2015
Event	Tenth Workshop on Statistical Machine Translation - Lisbon, Portugal Duration: 17 Sept 2015 → 18 Sept 2015 http://www.statmt.org/wmt15/

Conference

Conference	Tenth Workshop on Statistical Machine Translation
Abbreviated title	EMNLP 2015
Country/Territory	Portugal
City	Lisbon
Period	17/09/15 → 18/09/15
Internet address	http://www.statmt.org/wmt15/

Access to Document

10.18653/v1/W15-3050

http://aclweb.org/anthology/W15-3050

Cite this

@inproceedings{e9e18ac6ffea48d19bc5b55f22b89935,

title = "BEER 1.1: ILLC UvA submission to metrics and tuning task",

abstract = "We describe the submissions of ILLC UvA to the metrics and tuning tasks on WMT15. Both submissions are based on the BEER evaluation metric originally presented on WMT14 (Stanojevic´ and Sima{\textquoteright}an, 2014a). The main changes introduced this year are: (i) extending the learning-to-rank trained sentence level metric to the corpus level (but still decomposable to sentence level), (ii) incorporating syntactic ingredients based on dependency trees, and (iii) a technique for finding parameters of BEER that avoid “gaming of the metric” during tuning.",

author = "Milos Stanojevic and Khalil Sima'an",

year = "2015",

month = sep,

doi = "10.18653/v1/W15-3050",

language = "English",

pages = "396--401",

booktitle = "Proceedings of the Tenth Workshop on Statistical Machine Translation",

publisher = "Association for Computational Linguistics (ACL)",

note = "Tenth Workshop on Statistical Machine Translation, EMNLP 2015 ; Conference date: 17-09-2015 Through 18-09-2015",

url = "http://www.statmt.org/wmt15/",

}

TY - GEN

T1 - BEER 1.1: ILLC UvA submission to metrics and tuning task

AU - Stanojevic, Milos

AU - Sima'an, Khalil

PY - 2015/9

Y1 - 2015/9

N2 - We describe the submissions of ILLC UvA to the metrics and tuning tasks on WMT15. Both submissions are based on the BEER evaluation metric originally presented on WMT14 (Stanojevic´ and Sima’an, 2014a). The main changes introduced this year are: (i) extending the learning-to-rank trained sentence level metric to the corpus level (but still decomposable to sentence level), (ii) incorporating syntactic ingredients based on dependency trees, and (iii) a technique for finding parameters of BEER that avoid “gaming of the metric” during tuning.

AB - We describe the submissions of ILLC UvA to the metrics and tuning tasks on WMT15. Both submissions are based on the BEER evaluation metric originally presented on WMT14 (Stanojevic´ and Sima’an, 2014a). The main changes introduced this year are: (i) extending the learning-to-rank trained sentence level metric to the corpus level (but still decomposable to sentence level), (ii) incorporating syntactic ingredients based on dependency trees, and (iii) a technique for finding parameters of BEER that avoid “gaming of the metric” during tuning.

U2 - 10.18653/v1/W15-3050

DO - 10.18653/v1/W15-3050

M3 - Conference contribution

SP - 396

EP - 401

BT - Proceedings of the Tenth Workshop on Statistical Machine Translation

PB - Association for Computational Linguistics (ACL)

CY - Lisboa, Portugal

T2 - Tenth Workshop on Statistical Machine Translation

Y2 - 17 September 2015 through 18 September 2015

ER -

BEER 1.1: ILLC UvA submission to metrics and tuning task

Abstract / Description of output

Conference

Access to Document

Fingerprint

Cite this