Enhancing Best Analysis Selection and Parser Comparison

• Authors: HORÁK Aleš; SMRŽ Pavel; KADLEC Vladimír
• Year of publication: 2002
• Type: Article in Proceedings
• Conference: Proceedings of 5th International Conference on Text, Speech, and Dialogue (TSD 2002)
• MU Faculty or unit: Faculty of Informatics
• Web: http://nlp.fi.muni.cz/publications/tsd2002_hales_smrz_xkadlec/
• Field: Use of computers, robotics and its application
• Keywords: parsing
• Description: The paper discusses methods enhancing the selection of a ``best'' parsing tree from the output of natural language syntactic analysis. It presents a method for cutting away redundant parse trees based on the information obtained from a dependency tree-bank corpus. The effectivity of the enhanced parser is demonstrated by results of inter-system parser comparison. The test were run on the standard evaluation grammars (ATIS, CT and PT), our system outperforms the referential implementations.

Related projects

• Natural Language Processing Laboratory (with applications supporting education of people with limited sight)
• Syntactic analysis of natural language
• Human-computer interaction, dialog systems and assistive technologies