VI

As a prerequisite to translation of poetry, we implement the ability to produce translations with meter and rhyme for phrase-based MT, examine whether the hypothesis space of such a system is flexible enough to accomodate such constraints, and investigate the impact of such constraints on translation quality.

In this report, we describe our (NEUNLPLab) phrase-based statistical machine translation (SMT) system (NEUTrans) for the participation of news domain Chinese-to-English single-system translation task in the 5 China workshop on Machine Translation (CWMT2009). We submitted four translation results for this task. In this report, we first give an introduction of the framework and the key techniques...

This paper describes Sehda’s SMT (Syntactic Statistical Machine Translation) system submitted to the Korean-English track in the evaluation campaign of the IWSLT-05 workshop. The SMT is a phrase-based statistical system trained on linguistically processed parallel data.

Treatment of Markup in Statistical Machine Translation

This paper investigates the impact of misspelled words in statistical machine translation and proposes an extension of the translation engine for handling misspellings. The enhanced system decodes a word-based confusion network representing spelling variations of the input text. We present extensive experimental results on two translation tasks of increasing complexity which show how misspellin...

A novel and robust approach to improving statistical machine translation fluency is developed within a minimum Bayesrisk decoding framework. By segmenting translation lattices according to confidence measures over the maximum likelihood translation hypothesis we are able to focus on regions with potential translation errors. Hypothesis space constraints based on monolingual coverage are applied...

This paper describes Sehda’s SMT (Syntactic Statistical Machine Translation) system submitted to the Korean-English track in the evaluation campaign of the IWSLT-05 workshop. The SMT is a phrase-based statistical system trained on linguistically processed parallel data.

This paper describes Sehda’s SMT (Syntactic Statistical Machine Translation) system submitted to the Korean-English track in the evaluation campaign of the IWSLT-05 workshop. The SMT is a phrase-based statistical system trained on linguistically processed parallel data.

Attempts to estimate phrase translation probablities for statistical machine translation using iteratively-trained models have repeatedly failed to produce translations as good as those obtained by estimating phrase translation probablities from surface statistics of bilingual word alignments as described by Koehn, et al. (2003). We propose a new iteratively-trained phrase translation model tha...