As natural language is highly ambiguous even in restricted domains, interactive disambiguation is seen as a necessity for achieving more robust and user-friendly interactive systems, face-to-face translation systems and Dialogue-Based Machine Translation systems. We have proposed a methodology which distinguishes between two parts in a disambiguation module: an engine (languageand application-i...

The use of knowledge-based machine translation with controlled technical text can produce high-quality translations. However, building and maintaining knowledge bases can require signiicant time and eeort, since they typically involve hand-coding of semantic preferences. When a system can't disambiguate based on semantic preferences, it can initiate interactive disambiguation with the author to...

ITS-2 is an interactive sentence translation system under development at the LATL lab of the University of Geneva. In its current status, ITS-2 translates French sentences into English or English into French over a still restricted vocabulary of approximately 3'000 bilingual entries. The main objectives of this project are (i) to show some of the advantages of interactive approaches to NL trans...

Current machine translation systems require human revision to produce high-quality translations. This is achieved through a post-editing process or by means of an interactive human–computer collaboration. Most protocols belonging to the last scenario follow a left-to-right strategy, where the prefix of the translation is iteratively increased by successive validations and corrections made by th...

The current resurgence of interest in machine translation is partially attributable to the emergence of a variety of new paradigms, ranging from better translation aids and improved pre and post-editing methods, to highly interactive approaches and fully automated knowledge-based systems. This paper discusses each basic approach and provides some comparative analysis. It is argued that both int...