Objective
Intelligent dialogue is fundamental for the use of any natural language product operated by persons not fully aware of the system's capabilities or of the data it contains. It strengthens the overall system and enables mastery of the complex task of manipulating the natural language analysis components.
The MIS project addressed semantic representations of natural language sentences that could be effectively used to query and manipulate a multilingual structured document database. The project examined the feasibility of designing a core system for handling information retrieval requests to data and document bases in five of the major European languages.
The project addressed semantic representations of natural language sentences that could be effectively used to query and manipulate a multilingual structured document database. The project examined the feasibility of designing a core system for handling information retrieval requests to data and document bases in five of the major European languages.
The state of the art was investigated in those domains where advanced products could be developed which would only be marketed after a period of four to seven years. These included natural language analysis and generation, dialogue and planning, and knowledge representation and engineering, together with machine translation and information and information retrieval in a multilingual context. A market study was also undertaken to gain an appreciation of the economic viability of such products and the manner in which they should be exploited. Proposals were made concerning the underlying architecture of such a system based on the current state of the art, progress made and the competence of the partners. These propositions took into account the requirements of multilingualism and the types of knowledge involved. Investigations were carried out into the technical aspects of each language studied. It was recognised that full dialogues should be supported between the user and the system. The risk of constructing an architecture of a multilingual information system entirely around the concept of a dialogue planner was considered to be high. However, an acceptable paradigm for handling dialogue was nevertheless considered.
The state of the art was investigated in those domains where advanced products could be developed which would only be marketed after a period of four to seven years. These included natural language analysis and generation, dialogue and planning, and knowledge representation and engineering, together with machine translation and information and information retrieval in a multilingual context. A market study was also undertaken to gain an appreciation of the economic viability of such products and the manner in which they should be exploited.
Proposals were made concerning the underlying architecture of such a system based on the current state of the art, progress made and the competence of the partners. These propositions took into account the requirements of multilingualism and the types of knowledge involved.
Investigations were carried out into the technical aspects of each language studied. It was recognised that full dialogues should be supported between the user and the system. The risk of constructing an architecture of a multilingual information system entirely around the concept of a dialogue planner was considered to be high. However, an acceptable paradigm for handling dialogue was nevertheless considered.
Exploitation
The project resulted in a proposal for future collaborative development to provide a series of prototypes for architectural validation, as multilingual information is complex to design, and distinct architectural options are not yet evident.
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.
- humanities languages and literature linguistics
- natural sciences computer and information sciences databases
- natural sciences computer and information sciences knowledge engineering
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.
Data not available
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.
Data not available
Coordinator
38402 SAINT-MARTIN-D'HERES
France
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.