Marsal Gavaldà

Learn More
The Janus-III translation system translates spoken languages in limited domains. The current research focus is on is expanding beyond tasks involving a single semantic domain. The system combines translation components from multiple semantic domains into a uniied system using multi-domain parse lattices. This approach yields solutions to several problems(More)
JANUS is a multilingual speech-to-speech translation system designed to facilitate communication between two parties engaged in a spontaneousconversation in a limited domain. In this paper we describe our methodology for evaluating translation performance. Our current focus is on end-to-end evaluations-the evaluation of the translation capabilities of the(More)
JANUS-II is a research system to design and test components of speech-to-speech translation systems as well as a research prototype for such a system. We will focus on two aspects of the system: 1) new features of the speech recognition component JANUS-SR, 2) the end-to-end performance of JANUS-II, including a comparison of two machine translation(More)
This paper describes JANUS-III, our most recent version of the JANUS speech-to-speech translation system. We present an overview of the system and focus on how system design facilitates speech translation between multiple languages, and allows for easy adaptation to new source and target languages. We also describe our methodology for evaluation of(More)
A critical path in the development of natural language understanding (NLU) modules lies in the difficulty of defining a mapping from words to semantics: Usually it takes in the order of years of highly-skilled labor to develop a semantic mapping, e.g., in the form of a semantic grammar, that is comprehensive enough for a given domain. Yet, due to the very(More)
JANUS is a multilingual speech-to-speech translation system designed to facilitate communication between two parties engaged in a spontaneous conversation in a limited domain. In an attempt to achieve both robustness and translation accuracy we use two diier-ent translation components: the GLR module, designed to be more accurate , and the Phoenix module,(More)
As part of the JANUS speech-to-speech translation project, we have developed a robust translation system based on the information structures inherent to the task being performed. The basic premise is that the structure of the information to be transmitted is largely independent of the language used to encode it. Our system performs no syntactic analysis;(More)
The MT engine of the Janus speech-to-speech translation system is designed around four main principles: 1) an interlingua approach that allows the eecient addition of new languages, 2) the use of semantic grammars that yield low cost high quality translations for limited domains, 3) modular grammars that support easy expansion into new domains, and 4)(More)
We describe and experimentally evaluate an efficient method for automatically determining small clause boundaries in spontaneous speech. Our method applies an artificial neural network to information about part of speech and trigger words. We find that with a limited amount of data (less than 2500 words for the training set), a small sliding context window(More)