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 (Abeillé et al., 2003), viewing the task as a trade-off between generalizability and interpretability. We compare, for French, a supervised lexicalized parsing algorithm with a semi-supervised unlexicalized algorithm (Petrov et al., 2006) along the lines of (Crabbé 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. 1 Natural language parsing Despite the availability of annotated data, there have been relatively few works on French statistical parsing. Together with a treebank, the availability of several supervised or semi-supervised grammatical learning algorithms, primarily set up on English data, allows us to figure out how they