The GIVE-2 Nancy Generation Systems NA and NM

Alexandre Denis 1 Marilisa Amoia 1 Luciana Benotti 1 Laura Perez-Beltrachini 1 Claire Gardent 1 Tarik Osswlad 1
1 TALARIS - Natural Language Processing: representation, inference and semantics
Inria Nancy - Grand Est, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper presents the two instruction generation systems submitted by the team TALARIS at INRIA-Nancy to the GIVE- 2 challenge 2010. The first system (NM) aims to provide high-level instructions by giving freedom to the user and relies on an extension of the Dale and Reiter's in- cremental algorithm to generate the refer- ring expressions. The second system (NA) uses a more constrained directive naviga- tional strategy and relies on Reference Do- main Theory (Denis, 2010) to generate a wide range of referring expressions in- cluding pronouns, ellipsis and alternative phrases. The results show that despite NA is more successful than NM, NM is consid- ered a bit more enjoyable by the subjective assessment.
Document type :
Reports
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/inria-00541578
Contributor : Luciana Benotti <>
Submitted on : Tuesday, November 30, 2010 - 7:59:41 PM
Last modification on : Thursday, January 11, 2018 - 6:21:35 AM
Long-term archiving on : Friday, October 26, 2012 - 5:06:12 PM

File

GIVE-2-Nancy-1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00541578, version 1

Collections

Citation

Alexandre Denis, Marilisa Amoia, Luciana Benotti, Laura Perez-Beltrachini, Claire Gardent, et al.. The GIVE-2 Nancy Generation Systems NA and NM. [Research Report] 2010. ⟨inria-00541578⟩

Share

Metrics

Record views

303

Files downloads

210