Domain Adaptation for Machine Translation with Instance Selection

Ergun Biçici. Domain Adaptation for Machine Translation with Instance Selection. The Prague Bulletin of Mathematical Linguistics, 103:5-20, 2015. [doi:10.1515/pralin-2015-0001] Keyword(s): Machine Translation, Machine Learning, Domain Adaptation.

Domain adaptation for machine translation (MT) can be achieved by selecting training instances close to the test set from a larger set of instances. We consider 7 different domain adaptation strategies and answer 7 research questions, which give us a recipe for domain adaptation in MT. We perform English to German statistical MT (SMT) experiments in a setting where test and training sentences can come from different corpora and one of our goals is to learn the parameters of the sampling process. Domain adaptation with training instance selection can obtain 22% increase in target 2-gram recall and can gain up to 3.55 BLEU points compared with random selection. Domain adaptation with feature decay algorithm (FDA) not only achieves the highest target 2-gram recall and BLEU performance but also perfectly learns the test sample distribution parameter with correlation 0.99. Moses SMT systems built with FDA selected 10K training sentences is able to obtain F1 results as good as the baselines that use up to 2M sentences. Moses SMT systems built with FDA selected 50K training sentences is able to obtain 1 F1 point better results than the baselines.

QuEst for High Quality Machine Translation

Ergun Biçici and Lucia Specia. QuEst for High Quality Machine Translation. The Prague Bulletin of Mathematical Linguistics, 103:43-64, 2015. [doi:10.1515/pralin-2015-0003] Keyword(s): Machine Translation, Machine Learning, Performance Prediction.

In this paper we describe the use of QuEst, a framework that aims to obtain predictions on the quality of translations, to improve the performance of machine translation (MT) systems without changing their internal functioning. We apply QuEst to experiments with:

• multiple system translation ranking, where translations produced by different MT systems are ranked according to their estimated quality, leading to gains of up to 2.72 BLEU, 3.66 BLEUs, and 2.17 F1 points;
• n-best list re-ranking, where n-best list translations produced by an MT system are re-ranked based on predicted quality scores to get the best translation ranked top, which lead to improvements on sentence NIST score by 0.41 points;
• n-best list combination, where segments from an n-best list are combined using a lattice-based re-scoring approach that minimize word error, obtaining gains of 0.28 BLEU points; and
• the ITERPE strategy, which attempts to identify translation errors regardless of prediction errors (ITERPE) and build sentence-specific SMT systems (SSSS) on the ITERPE sorted instances identified as having more potential for improvement, achieving gains of up to 1.43 BLEU, 0.54 F1, 2.9 NIST, 0.64 sentence BLEU, and 4.7 sentence NIST points in English to German over the top 100 ITERPE sorted instances.