International audienceSurface realisation with grammars integrating flat semantics is known to be NP complete. In this paper, we present a new algorithm for surface realisation based on Feature Based Tree Adjoining Grammar (FTAG) which draws on the observation that an FTAG can be translated into a Regular Tree Grammar describing its derivation trees. We carry out an extensive testing of several variants of this algorithm using an automatically produced testsuite and compare the results obtained with those obtained using GenI, another FTAG based surface realiser
International audienceUsing a Feature-Based Lexicalised Tree Adjoining Grammar (FB-LTAG), we present...
Natural Language Generation (NLG) is the task of automatically producing natural language text to de...
We present dependency-based n-gram models for general-purpose, widecoverage, probabilistic sentence ...
Surface realisation from flat semantic formulae is known to be exponential in the length of the inpu...
Surface realisation is a subtask of natural language generation. It may be viewed as the inverse of ...
La réalisation de surface est une partie du processus global de génération de langue naturelle. Étan...
International audienceSurface realisers divide into those used in generation (NLG geared realisers) ...
International audienceWe present a novel algorithm for surface realisation with lexicalist grammars....
International audienceParsing efficiency within the context of tree adjoining grammars (TAGs) depend...
International audienceWe present GENSEM, a tool for generating input semantic representations for tw...
Colloque avec actes et comité de lecture. internationale.International audienceWe propose a semantic...
Current work in surface realization concentrates on the use of general, abstract algorithms that int...
International audienceWe present a simple, data-driven approach to generation from knowledge bases (...
La réalisation de surface est une partie du processus global de génération de langue naturelle. Étan...
International audienceSurface realisation (SR) maps a meaning representation to a sentence and can b...
International audienceUsing a Feature-Based Lexicalised Tree Adjoining Grammar (FB-LTAG), we present...
Natural Language Generation (NLG) is the task of automatically producing natural language text to de...
We present dependency-based n-gram models for general-purpose, widecoverage, probabilistic sentence ...
Surface realisation from flat semantic formulae is known to be exponential in the length of the inpu...
Surface realisation is a subtask of natural language generation. It may be viewed as the inverse of ...
La réalisation de surface est une partie du processus global de génération de langue naturelle. Étan...
International audienceSurface realisers divide into those used in generation (NLG geared realisers) ...
International audienceWe present a novel algorithm for surface realisation with lexicalist grammars....
International audienceParsing efficiency within the context of tree adjoining grammars (TAGs) depend...
International audienceWe present GENSEM, a tool for generating input semantic representations for tw...
Colloque avec actes et comité de lecture. internationale.International audienceWe propose a semantic...
Current work in surface realization concentrates on the use of general, abstract algorithms that int...
International audienceWe present a simple, data-driven approach to generation from knowledge bases (...
La réalisation de surface est une partie du processus global de génération de langue naturelle. Étan...
International audienceSurface realisation (SR) maps a meaning representation to a sentence and can b...
International audienceUsing a Feature-Based Lexicalised Tree Adjoining Grammar (FB-LTAG), we present...
Natural Language Generation (NLG) is the task of automatically producing natural language text to de...
We present dependency-based n-gram models for general-purpose, widecoverage, probabilistic sentence ...