Behind the Scenes in an Interactive Speech Translation System
نویسندگان
چکیده
This paper describes the facilities of Converser for Healthcare 4.0, a highly interactive speech translation system which enables users to verify and correct speech recognition and machine translation. Corrections are presently useful for real-time reliability, and in the future should prove applicable to offline machine learning. We provide examples of interactive tools in action, emphasizing semantically controlled backtranslation and lexical disambiguation, and explain for the first time the techniques employed in the tools’ creation, focusing upon compilation of a database of semantic cues and its connection to third-party MT engines. Planned extensions of our techniques to statistical MT are also discussed.
منابع مشابه
Translation and Hybridity in Scenes and Frames Semantics
The present study is a theoretical attempt to illustrate how Fillmore's Scenes and Frames Semantics (SFS) could be employed as a framework to portray the process of understanding and translating hybrid texts. It first reviews the origin of SFS; then it maps SFS onto Nida’s linguistic model of translation process and the Interpretive Theory of Translation; it examines in the next section, withi...
متن کاملPolice Interpreting: A View from the Australian Context
In the global village of today, more people have been moving and migrating than ever before creating a need for better communication. Thus community interpreting rose as a specialization serving the needs of members of the community who are unable to communicate with the system. Within this broad field of interpreting the specialist area of legal interpreting assumed a high position. However, l...
متن کاملThe Effect of Private Speech and Self-Regulation on Translation Quality among Iranian Translation Students: A Mixed-Methods Study
The current study presents findings from a mixed-methods study of investigating the self-regulatory role of private speech (self-talk) on students’ translation quality. The aim of the study was to validate the adapted version of a self-verbalization questionnaire. The construct validity and reliability of the scale were supported by the CFA which revealed that all items reached the acceptable f...
متن کاملWebDIPLOMAT: A Web-Based Interactive Machine Translation System
We have implemented an interactive, Web-based, chat-style machine translation system, supporting speech recognition and synthesis, localor thirdparty correction of speech recognition and machine translation output, and online learning. The underlying client-server architecture, implemented in Java, provides remote, distributed computation for the translation and speech subsystems. We further de...
متن کاملInteractive Real-time Translation via the Internet
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 ...
متن کامل