This paper presents an extension of Chiang’s hierarchical phrase-based (HPB) model, called Head-Driven HPB (HD-HPB), which incorporates head information in translation rules to better capture syntax-driven information, as well as improved reordering between any two neighboring non-terminals at any stage of a derivation to explore a larger reordering search space. Experiments on Chinese-English ...

We present in this paper a statistical framework that generates accurate and fluent product description from product attributes. Specifically, after extracting templates and learning writing knowledge from attribute-description parallel data, we use the learned knowledge to decide what to say and how to say for product description generation. To evaluate accuracy and fluency for the generated d...

Statistical MT has made great progress in the last few years, but current translation models are weak on re-ordering and target language fluency. Syntactic approaches seek to remedy these problems. In this paper, we take the framework for acquiring multi-level syntactic translation rules of (Galley et al., 2004) from aligned tree-string pairs, and present two main extensions of their approach: ...

Inspired by previous chunk-level reordering approaches to statistical machine translation, this paper presents two methods to improve the reordering at the chunk level. By introducing a new lattice weighting factor and by reordering the training source data, an improvement is reported on TER and BLEU. Compared to the previous chunklevel reordering approach, the BLEU score improves 1.4% absolute...

Automatic evaluation metrics for Machine Translation (MT) systems, such as BLEU and the related NIST metric, are becoming increasingly important in MT. This paper reports a novel method of calculating the confidence intervals for BLEU/NIST scores using bootstrapping. With this method, we can determine whether two MT systems are significantly different from each other. We study the effect of tes...

The paper presents an exploratory study of the translation processes for 12 student and 12 professional translators. We relate properties of the translators’ process data (eye movements and keystrokes) with the quality of the produced translations, using BLEU scores and human evaluation scores for fluency and accuracy to assess translation quality. We also investigate how BLEU scores correlate ...

The minimum Bayes risk (MBR) decoding objective improves BLEU scores for machine translation output relative to the standard Viterbi objective of maximizing model score. However, MBR targeting BLEU is prohibitively slow to optimize over k-best lists for large k. In this paper, we introduce and analyze an alternative to MBR that is equally effective at improving performance, yet is asymptoticall...

This paper describes speech translation from Amharic-to-English, particularly Automatic Speech Recognition (ASR) with post-editing feature and AmharicEnglish Statistical Machine Translation (SMT). ASR experiment is conducted using morpheme language model (LM) and phoneme acoustic model (AM). Likewise, SMT conducted using word and morpheme as unit. Morpheme based translation shows a 6.29 BLEU sc...

In most statistical machine translation (SMT) systems, bilingual segments are extracted via word alignment. However, there lacks systematic study as to what alignment characteristics can benefit MT under specific experimental settings such as the language pair or the corpus size. In this paper we produce a set of alignments by directly tuning the alignment model according to alignment F-score a...

Scrambling is acceptable reordering of verb arguments in languages such as Japanese and German. In automatic evaluation of translation quality, BLEU is the de facto standard method, but BLEU has only very weak correlation with human judgements in case of Japanese-toEnglish/English-to-Japanese translations. Therefore, alternative methods, IMPACT and RIBES, were proposed and they have shown much ...