Are ACT's scores increasing with better translation quality?
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.