The ClearTK-TimeML submission to TempEval 2013 competed in all English tasks: identifying events, identifying times, and identifying temporal relations. The system is a pipeline of machine-learning models, each with a small set of features from a simple morpho-syntactic annotation pipeline, and where temporal relations are only predicted for a small set of syntactic constructions and relation t...

To make a syntactic mechanism adequate for speech understanding requires several things. First, regarding the role of syntax, the parser should expect less work of the front-end and leave more work for the semantic back-end than has been traditional. Second, the parser should embody several design principles, including: `consider many simple syntactic hypotheses in parallel' andùse numeric comp...

In this paper, we introduce a system, Sentence Planning Using Description, which generates collocations within the paradigm of sentence planning. SPUD simultaneously constructs the semantics and syntax of a sentence using a Lexicalized Tree Adjoining Grammar (LTAG). This approach captures naturally and elegantly the interaction between pragmatic and syntactic constraints on descriptions in a se...

We introduce a notion of observation of a computational process on the basis of the observation of (the meaningful information couched by) the syntactic objects involved in the computation. This is formalized by means of observation mappings. We use them to give a semantic description of computational processes, an observable semantics , which is given on a purely syntactic basis; the observati...

The syntactic bootstrapping hypothesis suggests that children’s verb learning is guided by the structural cues that the linguistic context provides. However, the onset of syntactic bootstrapping in word learning is not well studied. To investigate the impact of linguistic information on word learning during early stages of language acquisition, we use a computational model of learning syntactic...

FIPSVox is a text-to-speech system for French developed at LATL. It is based on FIPS, a large-scale, multi-purpose, GBbased syntactic parser which produces detailed analyses and the MBROLA diphones-concatenation synthesizer. The syntactic information provided by the parser is directly exploited by the grapheme-to-phoneme module to handle heterophone homographs as well as French elision, denasal...

In this paper, we introduce a system, Sentence Planning Using Description, which generates collocations within the paradigm of sentence planning. SPUD simultaneously constructs the semantics and syntax of a sentence using a Lexicalized Tree Adjoining Grammar (LTAG). This approach captures naturally and elegantly the interaction between pragmatic and syntactic constraints on descriptions in a se...