Benoît Crabbé

On Statistical Parsing of French with Supervised and Semi-Supervised Strategies

This paper reports results on grammatical induction for French. We investigate how to best train a parser on the French Treebank (Abeille et al., 2003), viewing the task as a trade-off between generaliz-ability and interpretability. We compare, for French, a supervised lexicalized parsing algorithm with a semi-supervised un-lexicalized algorithm (Petrov et al., 2006) along the lines of (Crabbe and Candito, 2008). We report the best results known to us on French statistical parsing, that we obtained with the semi-supervised learning algorithm. The reported experiments can give insights for the task of grammatical learning for a morphologically-rich language, with a relatively limited amount of training data, annotated with a rather flat structure.

Bootstrapping the Syntactic Bootstrapper: Probabilistic Labeling of Prosodic Phrases

The syntactic bootstrapping hypothesis proposes that syntactic structure provides children with cues for learning the meaning of novel words. In this article, we address the question of how children might start acquiring some aspects of syntax before they possess a sizeable lexicon. The study presents two models of early syntax acquisition that rest on three major assumptions grounded in the infant literature: First, infants have access to phrasal prosody; second, they pay attention to words situated at the edges of prosodic boundaries; third, they know the meaning of a handful of words. The models take as input a corpus of French child-directed speech tagged with prosodic boundaries and assign syntactic labels to prosodic phrases. The excellent performance of these models shows the feasibility of the syntactic bootstrapping hypothesis, since elements of syntactic structure can be constructed by relying on prosody, function words, and a minimal semantic knowledge.

Neural Greedy Constituent Parsing with Dynamic Oracles.

Dynamic oracle training has shown substantial improvements for dependency parsing in various settings, but has not been explored for constituent parsing. The present article introduces a dynamic oracle for transition-based constituent parsing. Experiments on the 9 languages of the SPMRL dataset show that a neural greedy parser with morphological features , trained with a dynamic oracle, leads to accuracies comparable with the best non-reranking and non-ensemble parsers.

Multilingual discriminative lexicalized phrase structure parsing

We provide a generalization of discriminative lexicalized shift reduce parsing techniques for phrase structure grammar to a wide range of morphologically rich languages. The model is efficient and outperforms recent strong baselines on almost all languages considered. It takes advantage of a dependency based modelling of morphology and a shallow modelling of constituency boundaries.