Are ACT's scores increasing with better translation quality?
| Type of publication: | Conference paper |
| Citation: | Hajlaoui_ACL-WMT-13_2013 |
| Booktitle: | Are ACT's scores increasing with better translation quality? |
| Year: | 2013 |
| Month: | July |
| Pages: | 6 |
| Abstract: | This paper gives a detailed description of the ACT (Accuracy of Connective Translation) metric, a reference-based metric that assesses only connective translations. ACT relies on automatic word-level alignment (using GIZA++) between a source sentence and respectively the reference and candidate translations, along with other heuristics for comparing translations of discourse connectives. Using a dictionary of equivalents, the translations are scored automatically or, for more accuracy, semi-automatically. The accuracy of the ACT metric was assessed by human judges on sample data for English/French, English/Arabic, English/Italian and English/German translations; the ACT scores are within 2-5% of human scores. The actual version of ACT is available only for a limited language pairs. Consequently, we are participating only for the English/French and English/German language pairs. Our hypothesis is that ACT metric scores increase with better translation quality in terms of human evaluation. |
| Keywords: | ACT metric, discourse connectives, MT evaluation |
| Projects: |
Idiap COMTIS |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
