Skip to Main content Skip to Navigation
Conference papers

Surface Realisation from Knowledge-Bases

Bikash Gyawali 1 Claire Gardent 1 
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : We present a simple, data-driven approach to generation from knowledge bases (KB). A key feature of this approach is that grammar induction is driven by the extended domain of locality principle of TAG (Tree Adjoining Grammar); and that it takes into account both syntactic and semantic information. The resulting extracted TAG includes a unification based semantics and can be used by an existing surface realiser to generate sentences from KB data. Experimental evaluation on the KBGen data shows that our model outperforms a data-driven generate-and-rank approach based on an automatically induced probabilistic grammar; and is comparable with a handcrafted symbolic approach.
Document type :
Conference papers
Complete list of metadata

Cited literature [38 references]  Display  Hide  Download
Contributor : Claire Gardent Connect in order to contact the contributor
Submitted on : Wednesday, July 9, 2014 - 7:10:35 PM
Last modification on : Saturday, October 16, 2021 - 11:26:06 AM
Long-term archiving on: : Thursday, October 9, 2014 - 12:53:13 PM


Publisher files allowed on an open archive


  • HAL Id : hal-01021916, version 1



Bikash Gyawali, Claire Gardent. Surface Realisation from Knowledge-Bases. the 52nd Annual Meeting of the Association for Computational Linguistics, Jun 2014, Baltimore, United States. pp.424-434. ⟨hal-01021916⟩



Record views


Files downloads