Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shen, Libin | - |
dc.contributor.author | Champollion, Lucas | - |
dc.contributor.author | Joshi, Aravind | - |
dc.date.accessioned | 2013-07-06T03:01:18Z | - |
dc.date.available | 2013-07-06T03:01:18Z | - |
dc.date.issued | 2008-03-01 | - |
dc.identifier.citation | Shen, Libin, Lucas Champollion, and Aravind K. Joshi (2008). LTAG-spinal and the Treebank: A new resource for incremental, dependency and semantic parsing. Language Resources and Evaluation, 42(1): 1-19. | en_US |
dc.identifier.issn | 1574-020X | - |
dc.identifier.issn | 1572-8412 | - |
dc.identifier.uri | http://dx.doi.org/10.1007/s10579-007-9043-7 | - |
dc.identifier.uri | http://hdl.handle.net/2451/31837 | - |
dc.description.abstract | We introduce LTAG-spinal, a novel variant of traditional Lexicalized Tree Adjoining Grammar (LTAG) with desirable linguistic, computational and statistical properties. Unlike in traditional LTAG, subcategorization frames and the argument-adjunct distinction are left underspecified in LTAG-spinal. LTAG-spinal with adjunction constraints is weakly equivalent to LTAG. The LTAG-spinal formalism is used to extract an LTAG-spinal Treebank from the Penn Treebank with Propbank annotation. Based on Propbank annotation, predicate coordination and LTAG adjunction structures are successfully extracted. The LTAG-spinal Treebank makes explicit semantic relations that are implicit or absent from the original PTB. LTAG-spinal provides a very desirable resource for statistical LTAG parsing, incremental parsing, dependency parsing, and semantic parsing. This treebank has been successfully used to train an incremental LTAG-spinal parser and a bidirectional LTAG dependency parser. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Springer Netherlands | en_US |
dc.subject | Tree Adjoining Grammar | en_US |
dc.subject | LTAG-spinal | en_US |
dc.subject | Treebank | en_US |
dc.subject | Dependency parsing | en_US |
dc.title | LTAG-spinal and the Treebank: A new resource for incremental, dependency and semantic parsing | en_US |
dc.type | Preprint | en_US |
Appears in Collections: | Lucas Champollion's publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ltag-spinal.pdf | LTAG-spinal and the Treebank | 127.63 kB | Adobe PDF | View/Open |
Items in FDA are protected by copyright, with all rights reserved, unless otherwise indicated.