Skip navigation

LTAG-spinal and the Treebank: A new resource for incremental, dependency and semantic parsing

Authors: Shen, Libin
Champollion, Lucas
Joshi, Aravind
Keywords: Tree Adjoining Grammar;LTAG-spinal;Treebank;Dependency parsing
Issue Date: 1-Mar-2008
Publisher: Springer Netherlands
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.
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.
ISSN: 1574-020X
Appears in Collections:Lucas Champollion's publications

Files in This Item:
File Description SizeFormat 
ltag-spinal.pdfLTAG-spinal and the Treebank127.63 kBAdobe PDFView/Open

Items in FDA are protected by copyright, with all rights reserved, unless otherwise indicated.