Efficient Discontinuous Phrase-Structure Parsing via the Generalized Maximum Spanning Arborescence

Caio Corro (1) , Joseph Le Roux (2) , Mathieu Lacroix (2)

1 ILLC - Institute for Logic, Language and Computation
2 LIPN - Laboratoire d'Informatique de Paris-Nord

We present a new method for the joint task of tagging and non-projective dependency parsing. We demonstrate its usefulness with an application to discontinu-ous phrase-structure parsing where decoding lexicalized spines and syntactic derivations is performed jointly. The main contributions of this paper are (1) a reduction from joint tagging and non-projective dependency parsing to the Generalized Maximum Spanning Arborescence problem, and (2) a novel decoding algorithm for this problem through Lagrangian relaxation. We evaluate this model and obtain state-of-the-art results despite strong independence assumptions.

Domaines: Informatique et langage [cs.CL]; Intelligence artificielle [cs.AI]

Caio Corro, Joseph Le Roux, Mathieu Lacroix. Efficient Discontinuous Phrase-Structure Parsing via the Generalized Maximum Spanning Arborescence. 2017 Conference on Empirical Methods in Natural Language Processing, Sep 2017, Copenhagen, Denmark. pp.1644 - 1654. ⟨hal-01988864⟩