Publications
Authors:
  • Xavier Carreras , Miguel Ballesteros
Citation:
CoNLL 2015, Beijing, China, 30-31 July, 2015
Abstract:
We present a transition-based arc-eager
model to parse spinal trees, a dependencybased
representation that includes phrasestructure
information in the form of constituent
spines assigned to tokens. As a
main advantage, the arc-eager model can
utilize a rich set of features combining
dependency and constituent information,
while parsing in linear time. We describe
a set of conditions for the arc-eager system
to produce valid spinal structures. In
experiments using beam search we show
that the model obtains a good trade-off between
speed and accuracy, and yields state
of the art performance for both dependency
and constituent parsing measures.
Year:
2015
Report number:
2015/029
Attachments: