C
Claire Gardent
Researcher at Centre national de la recherche scientifique
Publications - 173
Citations - 3042
Claire Gardent is an academic researcher from Centre national de la recherche scientifique. The author has contributed to research in topics: Parsing & Natural language generation. The author has an hindex of 25, co-authored 167 publications receiving 2506 citations. Previous affiliations of Claire Gardent include Facebook & Saarland University.
Papers
More filters
Proceedings ArticleDOI
Creating Training Corpora for NLG Micro-Planners
TL;DR: This paper proposes the corpus generation framework as a novel method for creating challenging data sets from which NLG models can be learned which are capable of handling the complex interactions occurring during in micro-planning between lexicalisation, aggregation, surface realisation, referring expression generation and sentence segmentation.
Proceedings ArticleDOI
The WebNLG Challenge: Generating Text from RDF Data
TL;DR: The microplanning task is introduced, data preparation, evaluation methodology, participant results and a brief description of the participating systems are provided.
PatentDOI
Sequence-based structured prediction for semantic parsing
TL;DR: An approach for semantic parsing that uses a recurrent neural network to map a natural language question into a logical form representation of a KB query and shows how grammatical constraints on the derivation sequence can easily be integrated inside the RNN-based sequential predictor.
Proceedings ArticleDOI
Hybrid Simplification using Deep Semantics and Machine Translation
Shashi Narayan,Claire Gardent +1 more
TL;DR: A hybrid approach to sentence simplification which combines deep semantics and monolingual machine translation to derive simple sentences from complex ones that yields significantly simpler output that is both grammatical and meaning preserving.
Proceedings ArticleDOI
Generating Minimal Definite Descriptions
TL;DR: An alternative, constraint-based algorithm is presented that builds on existing related algorithms in that it produces minimal descriptions for sets of individuals using positive, negative and disjunctive properties and is integrated with surface realisation.