Objective
The primary objective of the project is to develop the technology and provide tools which will enable end users to interface, using natural-language, to computer applications systems, and to apply this technology successfully to obtain a pre-competitive product validated in selected end-user applications.
The approach is both application and end user centred. Applications centred in that the project will start with the analysis of existing applications, studying how to provide them with Natural Language (NL) interfaces which would satisfy their users. End-user centred in identifying and analysing the interests and requirements of end-users and specifying design requirements on future applications interfaces to allow them to include powerful natural language capabilities.
The project also has longer term, ambitious, but precise and feasible, objectives. It will place a number of strategic European IT companies in a leading position against foreign competitors, mainly large USA software products and services companies.
One of the foundations of the project is that two important aspects should be recognised and implemented:
- the integration of previous results from European Language Engineering projects
- compliance to formal and 'industry' standards, related to both operating environments (POSIX, Windows) and application inter-operability (CORBA, COM).
The design requirements specified will be consistent with and built upon emerging application interconnection standards, such as CORBA 2.0 or COM (OLE 2). These inter-operability standards may have to be extended to cover the requirements of a range of different applications and natural language interaction. A proposal will be produced to the appropriate bodies for extension to fully support MELISSA.
The RTD work is focused on three main areas:
- Study and definition of methods for the integration of a natural language interface into software applications, in general. Specification of the method to the level where it forms the basis for the MELISSA tool-set and could be used as a proposal for adoption as a public standard, to the appropriate bodies.
- Construction of a MELISSA tool-set, including an operational server, to be used by software developers of CORBA/COM compliant software applications to supply their final users with Natural Language interfacing for many of the available functions.
- Definition of a set of procedures and a general method to enable the use of the MELISSA tool-set to create Natural Language interfaces to already existing applications, deployed and exploited in the market or for internal use in the customer organisations, in cases where this would be a cost-effective solution.
A MELISSA based Natural Language interface will allow a user to request, for example: "I want to add a new customer in the clients database. The name of the new company is RSGHA, and it is located in Rue de la Liberté, 24 B-1080 Brussels".
In this way, commands can be simply and naturally expressed, freely providing access to an important part of any application's functions without the requirement of knowing the exact command or menu which is required to perform actions. Natural Language interfaces are recognised as potentially the most user friendly, mainly for input but also in some instances for output. Other benefits are obvious: little training required, direct integration with voice-recognition and generation systems, applicability for elderly/disabled people, etc.
The problems of providing an application with useful natural language capabilities are not trivial. A novel integration and extension of technologies is required to provide the means for translating user desires and commands stated in different natural languages to the application's own commands. A solution to these problems can however be generalised over all kind of applications. The techniques employed in interpretation and understanding of user sentences can be made common to all applications. Divergence also currently exists in protocols and interfaces to particular applications, facets which can be standardised.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
- natural sciences computer and information sciences databases
- natural sciences computer and information sciences software software applications
You need to log in or register to use this function
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
E - 28760 Tres Cantos
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.