Neural Greedy Constituent Parsing with Dynamic Oracles

Maximin Coavoux (1) , Benoît Crabbé (1)

1 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing

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.

Mots clés: NLP; parsing

Domaines: Informatique et langage [cs.CL]

Maximin Coavoux, Benoît Crabbé. Neural Greedy Constituent Parsing with Dynamic Oracles. Association for Computational Linguistics (ACL), 2016, Berlin, Germany. ⟨hal-01353734⟩