UEdin participation in the 1st Translation Memory Cleaning Shared Task

Christian Buck; Philipp Koehn

UEdin participation in the 1st Translation Memory Cleaning Shared Task

Christian Buck, Philipp Koehn

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

Abstract

We present our submission for the 1st Translation Memory Cleaning Shared Task. We treat the task as a 3-class classification problem and extract features that indicate (i) source sentence complexity, (ii) misalignments between source and target, and (iii) target sentence complexity. Our results show that focusing on the target side and finding ways to estimate the alignment quality between source and target yields expressive features which, together with a reliable classifier, produces competitive results. Our submission is ranked on 2nd place among 6 for the EN-DE language pair

Original language	English
Title of host publication	Proceedings of 2nd Workshop on Natural Language Processing for Translation Memories (NLP4TM 2016)
Place of Publication	Portorož, Slovenia
Number of pages	4
Publication status	Published - May 2016
Event	2nd Workshop on Natural Language Processing for Translation Memories - Portorož, Slovenia Duration: 28 May 2016 → 28 May 2016 http://rgcl.wlv.ac.uk/nlp4tm2016/

Conference

Conference	2nd Workshop on Natural Language Processing for Translation Memories
Abbreviated title	NLP4TM 2016
Country/Territory	Slovenia
City	Portorož
Period	28/05/16 → 28/05/16
Internet address	http://rgcl.wlv.ac.uk/nlp4tm2016/

Access to Document

ChristianBuck-TM_Cleaning_Shared_TaskFinal published version, 202 KB

Cite this

@inproceedings{7138b7e8169048a589df479f324f4183,

title = "UEdin participation in the 1st Translation Memory Cleaning Shared Task",

abstract = "We present our submission for the 1st Translation Memory Cleaning Shared Task. We treat the task as a 3-class classification problem and extract features that indicate (i) source sentence complexity, (ii) misalignments between source and target, and (iii) target sentence complexity. Our results show that focusing on the target side and finding ways to estimate the alignment quality between source and target yields expressive features which, together with a reliable classifier, produces competitive results. Our submission is ranked on 2nd place among 6 for the EN-DE language pair",

author = "Christian Buck and Philipp Koehn",

year = "2016",

month = may,

language = "English",

booktitle = "Proceedings of 2nd Workshop on Natural Language Processing for Translation Memories (NLP4TM 2016)",

note = "2nd Workshop on Natural Language Processing for Translation Memories , NLP4TM 2016 ; Conference date: 28-05-2016 Through 28-05-2016",

url = "http://rgcl.wlv.ac.uk/nlp4tm2016/",

}

TY - GEN

T1 - UEdin participation in the 1st Translation Memory Cleaning Shared Task

AU - Buck, Christian

AU - Koehn, Philipp

PY - 2016/5

Y1 - 2016/5

N2 - We present our submission for the 1st Translation Memory Cleaning Shared Task. We treat the task as a 3-class classification problem and extract features that indicate (i) source sentence complexity, (ii) misalignments between source and target, and (iii) target sentence complexity. Our results show that focusing on the target side and finding ways to estimate the alignment quality between source and target yields expressive features which, together with a reliable classifier, produces competitive results. Our submission is ranked on 2nd place among 6 for the EN-DE language pair

AB - We present our submission for the 1st Translation Memory Cleaning Shared Task. We treat the task as a 3-class classification problem and extract features that indicate (i) source sentence complexity, (ii) misalignments between source and target, and (iii) target sentence complexity. Our results show that focusing on the target side and finding ways to estimate the alignment quality between source and target yields expressive features which, together with a reliable classifier, produces competitive results. Our submission is ranked on 2nd place among 6 for the EN-DE language pair

M3 - Conference contribution

BT - Proceedings of 2nd Workshop on Natural Language Processing for Translation Memories (NLP4TM 2016)

CY - Portorož, Slovenia

T2 - 2nd Workshop on Natural Language Processing for Translation Memories

Y2 - 28 May 2016 through 28 May 2016

ER -

UEdin participation in the 1st Translation Memory Cleaning Shared Task

Abstract

Conference

Access to Document

Fingerprint

Cite this