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.
Original language | English (US) |
---|---|
Pages (from-to) | 1-19 |
Number of pages | 19 |
Journal | Language Resources and Evaluation |
Volume | 42 |
Issue number | 1 |
DOIs | |
State | Published - Mar 2008 |
Keywords
- Dependency parsing
- LTAG-spinal
- Tree adjoining grammar
- Treebank
ASJC Scopus subject areas
- Language and Linguistics
- Education
- Linguistics and Language
- Library and Information Sciences