Fabio Ciravegna and Nicola Cancedda. Integrating shallow and linguistic techniques for information extraction from text. In Proceedings of the Fourth Congress of the Italian Association for Artificial Intelligence, Firenze, Italy, October 1995. To be published in Lecture Notes in Artificial Intelligence, Springer-Verlag. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Information Extraction Strategies for Thai Documents - Sukhahuta, Smith (2001) (Correct)
....Often information extraction based on regular expressions fails to capture the information from the natural language text without a lot of knowledge of the domain and document class. Furthermore, the integration of linguistic approaches with pattern matching can improve the extraction results [6]. In [25, 24] the extraction templates are represented by the linguistic patterns using notation of subject, object, and direct object as one of the constraints to help capture more specific information from text documents. However, the success of this approach relies on the performance of the ....
F. Ciravegna and N. Cancedda. Integrating shallow and linguistic techniques for information extraction from text. In Proceedings of the Fourth Conference of the Italian Association for Artificial Intelligence, pages 127--138, 1995.
Controlling Bidirectional Parsing for - Efficient Text Analysis Self-citation (Ciravegna) (Correct)
No context found.
Fabio Ciravegna and Nicola Cancedda. Integrating shallow and linguistic techniques for information extraction from text. In Proceedings of the Fourth Congress of the Italian Association for Artificial Intelligence, Firenze, Italy, October 1995. To be published in Lecture Notes in Artificial Intelligence, Springer-Verlag.
On Parsing Control For Efficient Text Analysis - Fabio Ciravegna Self-citation (Ciravegna) (Correct)
.... management uses the preprocessor results to control the parser: the segmentation results are used to split the sentence analysis in two steps (i.e. segment parsing and segment combination) whereas information about the templates is used, among others, as heuristics to sort the tasks in the agenda [1]. During segment parsing the segments produced by the preprocessor are analyzed, producing basic constituents such as simple NPs, PPs, and so on. This means that the combination of edges crossing the boundaries of segments is prevented (i.e. delayed until segment combination) by an appropriate ....
....an acceptable template score, the tasks with lower segmentation scores are pruned. This strategy also allows to overcome possible segmentation errors [2] 3. Parser at Work The modules described so far have been integrated in a system for text understanding currently under development at IRST [1]. The system has been implemented in Common Lisp. As for the linguistic modules of the system, both syntactic and semantic information are encoded using a formalism based on Typed Feature Structures. We have been experimenting on a corpus composed of short news (average 70 words) taken from the ....
Fabio Ciravegna and Nicola Cancedda. Integrating shallow and linguistic techniques for information extraction from text. In Proceedings of the Fourth Congress of the Italian Association for Artificial Intelligence, Firenze, Italy, October 1995. To be published in Lecture Notes in Artificial Intelligence, Springer-Verlag.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC