MERT

We present a unified approach to perform- ing minimum risk training and minimum Bayes risk (MBR) decoding with BLEU in a phrase-based model. Key to our ap- proach is the …...

Translation systems are generally trained to optimize BLEU, but many alternative metrics are available. We explore how optimizing toward various automatic evaluation metrics (BLEU, METEOR, NIST, TER) affects the re- …...

Statistical machine translation systems are normally optimised for a chosen gain func- tion (metric) by using MERT to find the best model weights. This algorithm suffers from stability problems and …...

There has been a proliferation of recent work on SMT tuning algorithms capable of han- dling larger feature sets than the traditional MERT approach. We analyze a number of these …...

We study a problem with pairwise ranking optimization (PRO): that it tends to yield too short translations. We find that this is partially due to the inadequate smoothing in PRO’s …...

We present a fast and scalable online method for tuning statistical machine trans- lation models with large feature sets. The standard tuning algorithm—MERT—only scales to tens of features. Recent discrimi- …...

We introduce a new large-scale discrimina- tive learning algorithm for machine translation that is capable of learning parameters in mod- els with extremely sparse features. To ensure their reliable estimation …...

While large-scale discriminative training has triumphed in many NLP problems, its defi- nite success on machine translation has been largely elusive. Most recent efforts along this line are not scalable …...

Parameter tuning is an important problem in statistical machine translation, but surpris- ingly, most existing methods such as MERT, MIRA and PRO are agnostic about search, while search errors could …...

We study the impact of source length and verbosity of the tuning dataset on the per- formance of parameter optimizers such as MERT and PRO for statistical machine translation. In …...

We present APRO, a new method for machine translation tuning that can handle large feature sets. As opposed to other popular methods (e.g., MERT, MIRA, PRO), which involve ran- domness …...

The log-linear combination of different features is an important component of SMT systems. It allows for the easy in- tegartion of models into the system and is used during decoding …...

In this paper, we describe our submis- sion to WMT 2015 Tuning Task. We integrate a dependency-based MT evalu- ation metric, RED, to Moses and com- pare it with BLEU …...

Parameter tuning is a key problem for sta- tistical machine translation (SMT). Most popular parameter tuning algorithms for SMT are agnostic of decoding, result- ing in parameters vulnerable to search …...