Language Resources and Evaluation

, Volume 42, Issue 1, pp 1–19

LTAG-spinal and the Treebank

A new resource for incremental, dependency and semantic parsing
Article

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.

Keywords

Tree Adjoining Grammar LTAG-spinal Treebank Dependency parsing 

Abbreviation

LTAG

Lexicalized Tree Adjoining Grammar

Copyright information

© Springer Science+Business Media B.V. 2007

Authors and Affiliations

  • Libin Shen
    • 1
  • Lucas Champollion
    • 2
  • Aravind K. Joshi
    • 3
  1. 1.BBN TechnologiesCambridgeUSA
  2. 2.Department of LinguisticsUniversity of PennsylvaniaPhiladelphiaUSA
  3. 3.Department of Computer and Information ScienceUniversity of PennsylvaniaPhiladelphiaUSA

Personalised recommendations