Skip to Main content Skip to Navigation
Conference papers

Generating Grammar Exercises

Laura Perez-Beltrachini 1 Claire Gardent 1 German Kruszewski 1
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Grammar exercises for language learning fall into two distinct classes: those that are based on ''real life sentences'' extracted from existing documents or from the web; and those that seek to facilitate language acquisition by presenting the learner with exercises whose syntax is as simple as possible and whose vocabulary is restricted to that contained in the textbook being used. In this paper, we introduce a framework (called gramex) which permits generating the second type of grammar exercises. Using generation techniques, we show that a grammar can be used to semi-automatically generate grammar exercises which target a specific learning goal; are made of short, simple sentences; and whose vocabulary is restricted to that used in a given textbook.
Document type :
Conference papers
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download
Contributor : Claire Gardent <>
Submitted on : Saturday, December 22, 2012 - 11:05:18 AM
Last modification on : Wednesday, January 6, 2021 - 6:48:02 AM
Long-term archiving on: : Saturday, March 23, 2013 - 3:46:42 AM


Files produced by the author(s)


  • HAL Id : hal-00768610, version 1



Laura Perez-Beltrachini, Claire Gardent, German Kruszewski. Generating Grammar Exercises. The 7th Workshop on Innovative Use of NLP for Building Educational Applications, NAACL-HLT Worskhop 2012, Jun 2012, Montreal, Canada. pp.147-157. ⟨hal-00768610⟩



Record views


Files downloads