Objective
Because of its great industrial and social interest, Machine Translation (MT) has received considerable attention for a long time. The EuTrans project is aimed at using Example-Based (EB) techniques for developing MT systems for limited-domain tasks which require text and/or speech input.
In the first phase of EuTrans (LTR -- Open Scheme #20268) basic demonstration systems for text-input and speech-input translation have been developed. These prototypes rely on EB techniques for learning a kind of finite-state translation models, known as Subsequential Transducers. These models lend themselves particularly well to being integrated with acoustic-phonetic, lexical and syntactic models in order to perform speech-input MT. This allows the building of systems in which all the models required for each new application are automatically learned from training data.
In the first-phase of EuTrans, these techniques have been applied to a medium-sized person-to-person communication task in the hotel domain, and the results have been shown to be superior to those obtained by low-cost rule-based commercial translation systems.
In order to deal with more realistic and complex translation tasks, additional research is required: (1) to further improve the baseline finite-state modeling techniques explored during the first phase; (2) to explore emerging statistical approaches that could be complementary to these techniques; and (3) to study adequate methods for non-expensive training data collection in limited-domain applications. These constitute the research objectives of the present project. Following the successful paradigm started in the first phase, particular attention will be paid to the tight integration of translation and speech recognition, with the aim of achieving a high degree of robustness in speech-input operation.
The feasibility of these EB techniques and their usefulness from a final-user perspective will be demonstrated by building both text-input and speech-input prototypes following user-centered methodologies.
Important benefits are expected from the results: Example-Based approaches allow for automatically building MT systems from training examples of each considered task. This is expected to reduce the development costs of MT systems in many specific domains, as compared with more traditional Knowledge-Based approaches. On the other hand, tight integration of translation and speech models are expected to allow for low-cost, real-time, robust speech-input translation for limited-domain applications, in contrast with the comparatively high computational demands often entailed by more conventional approaches based on a significantly less robust "first-recognition then-translation" paradigm.
Programme(s)
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Topic(s)
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Call for proposal
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Data not available
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Funding Scheme
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Coordinator
46022 Valencia
Spain
The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.