Exploring beam-based shift-reduce dependency parsing with DyALog: Results from the SPMRL 2013 shared task

Éric Villemonte de La Clergerie (1)

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

The SPMRL 2013 shared task was the op- portunity to develop and test, with promising results, a simple beam-based shift-reduce de- pendency parser on top of the tabular logic programming system DYALOG. The parser was also extended to handle ambiguous word lattices, with almost no loss w.r.t. disam- biguated input, thanks to specific training, use of oracle segmentation, and large beams. We believe that this result is an interesting new one for shift-reduce parsing.

Mots clés: parsing; shift-reduce parsing

Domaines: Informatique et langage [cs.CL]

Éric Villemonte de La Clergerie. Exploring beam-based shift-reduce dependency parsing with DyALog: Results from the SPMRL 2013 shared task. 4th Workshop on Statistical Parsing of Morphologically Rich Languages (SPMRL'2013), Oct 2013, Seattle, United States. ⟨hal-00879129⟩