Content area

Abstract

In this paper, we present an approach for automatically creating a combinatory categorial grammar (CCG) treebank from a dependency treebank for the subject–object–verb language Hindi. Rather than a direct conversion from dependency trees to CCG trees, we propose a two stage approach: a language independent generic algorithm first extracts a CCG lexicon from the dependency treebank. An exhaustive CCG parser then creates a treebank of CCG derivations. We also discuss special cases of this generic algorithm to handle linguistic phenomena specific to Hindi. In doing so we extract different constructions with long-range dependencies like coordinate constructions and non-projective dependencies resulting from constructions like relative clauses, noun elaboration and verbal modifiers.

Details

Title
Hindi CCGbank: A CCG treebank from the Hindi dependency treebank
Author
Bharat Ram Ambati 1 ; Deoskar, Tejaswini 2 ; Steedman, Mark 1 

 ILCC, School of Informatics, University of Edinburgh, Edinburgh, UK 
 Institute for Logic, Language and Computation, University of Amsterdam, Amsterdam, The Netherlands 
Pages
67-100
Publication year
2018
Publication date
Mar 2018
Publisher
Springer Nature B.V.
ISSN
1574020X
e-ISSN
1574-0218
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
1999917554
Copyright
Language Resources and Evaluation is a copyright of Springer, (2017). All Rights Reserved.