We explore how the translation direction in the tuning set used for statistical machine translation affects the translation results. We explore this issue for three language pairs. While the results on different metrics are somewhat conflicting, using tuning data translated in the same direction as the translation systems tends to give the best length ratio and Meteor scores for all language pa...

We investigated an e cient decoding algorithm for statistical machine translation. Compared to the other algorithms, this new algorithm is applicable to di erent translation models, and it is much faster. Experiments showed that the algorithm achieved an overall performance comparable to the state of the art decoding algorithms.

Tree-to-tree Statistical Machine Translation models require the use of syntactic tree structures of both the source and target side in learning rules to guide the translation process. In order to accomplish the task, available treebanks for different languages are used as the main resources to collect necessary information to handle the translation task. However, since each treebank has its own...

German particle verbs are a type of multi word expression which is often compositional with respect to a base verb. If they are compositional they tend to express the same types of semantic arguments, but they do not necessarily express them in the same syntactic subcategorization frame: some arguments may be expressed by differing syntactic subcategorization slots and other arguments may be on...

We discuss different strategies for smoothing the phrasetable in Statistical MT, and give results over a range of translation settings. We show that any type of smoothing is a better idea than the relativefrequency estimates that are often used. The best smoothing techniques yield consistent gains of approximately 1% (absolute) according to the BLEU metric.

In this paper, we describe the system and approach used by Institute for Infocomm Research (IR) for IWSLT 2010 spoken language translation evaluation campaign. We apply system combination on top of two kinds of statistical machine translation system, namely, phrase-based system and syntaxbased system. Experimental results show consistent improvements on DIALOG Task.

This paper proposes a method to integrate multiple segmentation schemes into a single statistical machine translation (SMT) system by characterizing the source language side and merging identical translation pairs of differently segmented SMT models. Experimental results translating Japanese into English revealed that the proposed method of integrating multiple segmentation schemes outperforms ...

We study the relationship between word order freedom and preordering in statistical machine translation. To assess word order freedom, we first introduce a novel entropy measure which quantifies how difficult it is to predict word order given a source sentence and its syntactic analysis. We then address preordering for two target languages at the far ends of the word order freedom spectrum, Ger...

While phrase-based statistical machine translation systems currently deliver state-of-theart performance, they remain weak on word order changes. Current phrase reordering models can properly handle swaps between adjacent phrases, but they typically lack the ability to perform the kind of long-distance reorderings possible with syntax-based systems. In this paper, we present a novel hierarchica...

In statistical machine translation, large numbers of parallel sentences are required to train the model parameters. However, plenty of the bilingual language resources available on web are aligned only at the document level. To exploit this data, we have to extract the bilingual sentences from these documents. The common method is to break the documents into segments using predefined anchor wor...