A new approach for Interactive Machine Translation where the author interacts during the creation or the modification of the document is proposed. The explanation of an ambiguity or an error for the purposes of correction does not use any concepts of the underlying linguistic theory : it is a reformulation of the erroneous or ambiguous sentence. The interaction is limited to the analysis step o...

We argue that the conventional approach to Interactive Machine Translation is not the best way to provide assistance to skilled translators, and propose an alternative whose central feature is the use of the target text as a medium of interaction. We describe an automatic word-completion system intended to serve as a vehicle for exploring the feasibility of this new approach, and give results i...

The Internet offers a tremendous opportunity for experiments with real-time machine translation (MT) dialogues. Interchanges may be typed, or speech recognition (SR) techniques might be used to accept spoken input. In either case, given the number of ambiguities still escaping automatic resolution, interactive disambiguation for both components seems likely to remain important in many Internet ...

In this paper, we present a new interactive 2D deformation technique to make caricatures with extreme exaggerations. In our technique, we use simplices as deformation primitives. User defined source and target shapes of each simplex primitive define local coordinates. These local coordinates determine a unique translation vector for any given point in 2D space. We also provide a set of blending...

This work is in the context of TRANSTYPE, a system that watches over the user as he or she types a translation and repeatedly suggests completions for the text already entered. The user may either accept, modify, or ignore these suggestions. The system’s proposals are selected and scored using a linear combination of a trigram language model and a translation model. We investigate the issue of ...

Text prediction is a form of interactive machine translation that is well suited to skilled translators. In principle it can assist in the production of a target text with minimal disruption to a translator’s normal routine. However, recent evaluations of a prototype prediction system showed that it significantly decreased the productivity of most translators who used it. In this paper, we anal...

Analyses of computer aided translation typically focus on either frontend interfaces and human effort, or backend translation and machine learnability of corrections. However, this distinction is artificial in practice since the frontend and backend must work in concert. We present the first holistic, quantitative evaluation of these issues by contrasting two assistive modes: postediting and in...

The term metadiscourse rarely appears in translation studies despite the continuously growing body of research on discourse markers in different genres and through various perspectives. Translation as a product that needs to observe such markers for their communicative power and contribution to the overall coherence of a text within a context has not been satisfactorily studied. Motivated by su...

We present JANUS-II, a large scale system effort aimed at interactive spoken language translation. JANUS-II now accepts spontaneous conversational speech in a limited domain in English, German or Spanish and produces output in German, English, Spanish, Japanese and Korean. The challenges of coarticulated, disfluent, ill-formed speech are manifold, and have required advances in acoustic modeling...

We describe an open source workbench that offers advanced computer aided translation (CAT) functionality: post-editing machine translation (MT), interactive translation prediction (ITP), visualization of word alignment, extensive logging with replay mode, integration with eye trackers and e-pen.