Efficient Sentence Parsing with Language Specific Features:A Case Study of Czech
| Authors | |
|---|---|
| Year of publication | 2001 |
| Type | Article in Proceedings |
| Conference | Proceedings of the IWPT'2001 (the 7th International Workshop on Parsing Technologies) |
| MU Faculty or unit | |
| Citation | |
| Web | http://nlp.fi.muni.cz/publications/iwpt2001_hales_smrz/ |
| Field | Computer hardware and software |
| Keywords | natural language; parsing |
| Description | The paper presents two optimalizations of standard parsing techniques applied to Czech as a representative of a free word order language with rich morphology. Our approach is based on features that take advantage of particular knowledge of language specific properties. The first method involves a special type of merging possible due to the agreement fulfillment. Another use of language specific features lies in the exploitation of verb valency frames for probabilistic ordering of parsing output. |
| Related projects: |