Author:
Publisher:
ISBN:
Category :
Languages : en
Pages : 11
Book Description
Through their involvement in the Tipster project the Computing Research Laboratory at New Mexico State University and the Computer Science Department at Brandeis University are developing a method for identifying articles of interest and extracting and storing specific kinds of information from large volumes of Japanese and English texts. We intend that the method be general and extensible. The techniques involved are not explicitly tied to these two languages nor to a particular subject area. Development for Tipster has been going on since September, 1992. The system we have used for the MUC-4 tests has only implemented some of the features we plan to include in our final Tipster system. It relies intensively on statistics and on context-free text marking to generate templates. Some more detailed parsing has been added for a limited lexicon, but lack of fuller coverage places an inherent limit on its performance. Most of the information produced in our MUC templates is arrived at by probing the text which surrounds 'significant' words for the template type being generated, in order to find appropriately tagged fillers for the template fields.
CRL/NMSU and Brandeis: Description of the MucBruce System as Used for MUC-4
Author:
Publisher:
ISBN:
Category :
Languages : en
Pages : 11
Book Description
Through their involvement in the Tipster project the Computing Research Laboratory at New Mexico State University and the Computer Science Department at Brandeis University are developing a method for identifying articles of interest and extracting and storing specific kinds of information from large volumes of Japanese and English texts. We intend that the method be general and extensible. The techniques involved are not explicitly tied to these two languages nor to a particular subject area. Development for Tipster has been going on since September, 1992. The system we have used for the MUC-4 tests has only implemented some of the features we plan to include in our final Tipster system. It relies intensively on statistics and on context-free text marking to generate templates. Some more detailed parsing has been added for a limited lexicon, but lack of fuller coverage places an inherent limit on its performance. Most of the information produced in our MUC templates is arrived at by probing the text which surrounds 'significant' words for the template type being generated, in order to find appropriately tagged fillers for the template fields.
Publisher:
ISBN:
Category :
Languages : en
Pages : 11
Book Description
Through their involvement in the Tipster project the Computing Research Laboratory at New Mexico State University and the Computer Science Department at Brandeis University are developing a method for identifying articles of interest and extracting and storing specific kinds of information from large volumes of Japanese and English texts. We intend that the method be general and extensible. The techniques involved are not explicitly tied to these two languages nor to a particular subject area. Development for Tipster has been going on since September, 1992. The system we have used for the MUC-4 tests has only implemented some of the features we plan to include in our final Tipster system. It relies intensively on statistics and on context-free text marking to generate templates. Some more detailed parsing has been added for a limited lexicon, but lack of fuller coverage places an inherent limit on its performance. Most of the information produced in our MUC templates is arrived at by probing the text which surrounds 'significant' words for the template type being generated, in order to find appropriately tagged fillers for the template fields.
Fourth Message Understanding Conference, (MUC-4)
Author:
Publisher:
ISBN:
Category : Artificial intelligence
Languages : en
Pages : 418
Book Description
Publisher:
ISBN:
Category : Artificial intelligence
Languages : en
Pages : 418
Book Description
ACL Proceedings
Author: ACL
Publisher: Morgan Kaufmann
ISBN: 9781558609853
Category : Computers
Languages : en
Pages : 420
Book Description
Proceedings of the Conferences on Applied Natural Language Processing, sponsored by the Association for Computational Linguistics.
Publisher: Morgan Kaufmann
ISBN: 9781558609853
Category : Computers
Languages : en
Pages : 420
Book Description
Proceedings of the Conferences on Applied Natural Language Processing, sponsored by the Association for Computational Linguistics.
Fifth Conference on Applied Natural Language Processing
Author: Association for Computational Linguistics
Publisher:
ISBN:
Category : Computational linguistics
Languages : en
Pages : 420
Book Description
Publisher:
ISBN:
Category : Computational linguistics
Languages : en
Pages : 420
Book Description
Computational Linguistics
Author:
Publisher:
ISBN:
Category : Computational linguistics
Languages : en
Pages : 728
Book Description
Publisher:
ISBN:
Category : Computational linguistics
Languages : en
Pages : 728
Book Description