APRO: All-Pairs Ranking Optimization for MT Tuning
نویسندگان
چکیده
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 randomness and require multiple runs to obtain a reliable result, APRO gives the same result on any run, given initial feature weights. APRO follows the pairwise ranking approach of PRO (Hopkins and May, 2011), but instead of ranking a small sampled subset of pairs from the kbest list, APRO efficiently ranks all pairs. By obviating the need for manually determined sampling settings, we obtain more reliable results. APRO converges more quickly than PRO and gives similar or better translation results.
منابع مشابه
PORT: a Precision-Order-Recall MT Evaluation Metric for Tuning
Many machine translation (MT) evaluation metrics have been shown to correlate better with human judgment than BLEU. In principle, tuning on these metrics should yield better systems than tuning on BLEU. However, due to issues such as speed, requirements for linguistic resources, and optimization difficulty, they have not been widely adopted for tuning. This paper presents PORT 1 , a new MT eval...
متن کاملRobust Tuning Datasets for Statistical Machine Translation
We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyperparameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning algorithms. This is an under-explored research direction, which can allow better parameter tuning. In this paper, we achieve this goal by selecting a subset of the ...
متن کاملTuning as Ranking
We offer a simple, effective, and scalable method for statistical machine translation parameter tuning based on the pairwise approach to ranking (Herbrich et al., 1999). Unlike the popular MERT algorithm (Och, 2003), our pairwise ranking optimization (PRO) method is not limited to a handful of parameters and can easily handle systems with thousands of features. Moreover, unlike recent approache...
متن کاملHUME: Human UCCA-Based Evaluation of Machine Translation
Human evaluation of machine translation normally uses sentence-level measures such as relative ranking or adequacy scales. However, these provide no insight into possible errors, and do not scale well with sentence length. We argue for a semantics-based evaluation, which captures what meaning components are retained in the MT output, thus providing a more fine-grained analysis of translation qu...
متن کاملMutual Information and Diverse Decoding Improve Neural Machine Translation
Sequence-to-sequence neural translation models learn semantic and syntactic relations between sentence pairs by optimizing the likelihood of the target given the source, i.e., p(y|x), an objective that ignores other potentially useful sources of information. We introduce an alternative objective function for neural MT that maximizes the mutual information between the source and target sentences...
متن کامل