- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Automatic Translation feature is available on CiNii Labs
- Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Description
This paper describes a wide-coverage Japanese grammar based on HPSG. The aim of this work is to see the coverage and accuracy attainable using an underspecified grammar. Underspecification, allowed in a typed feature structure formalism, enables us to write down a wide-coverage grammar concisely. The grammar we have implemented consists of only 6 ID schemata, 68 lexical entries (assigned to functional words), and 63 lexical entry templates (assigned to parts of speech (POSs) ). Furthermore, word-specific constraints such as subcategorization of verbs are not fixed in the grammar. However, this grammar can generate parse trees for 87% of the 10000 sentences in the Japanese EDR corpus. The dependency accuracy is 78% when a parser uses the heuristic that every bunsetsu is attached to the nearest possible one.
Journal
-
- Proceedings of the 17th international conference on Computational linguistics -
-
Proceedings of the 17th international conference on Computational linguistics - 2 876-880, 1998-01-01
Association for Computational Linguistics (ACL)
