Chunyang Xiao, Marc Dymetman, Claire Gardent
ACL, Berlin, Germany, August 7-12, 2016
We propose an approach for semantic
parsing that uses a recurrent neural network
to map a natural language question
into a logical form representation of a
KB query. Building on recent work by
(Wang et al., 2015), the interpretable logical
forms, which are structured objects
obeying certain constraints, are enumerated
by an underlying grammar and are
paired with their canonical realizations.
In order to use sequence prediction, we
need to sequentialize these logical forms.
We compare three sequentializations: a
direct linearization of the logical form, a
linearization of the associated canonical
realization, and a sequence consisting of
derivation steps relative to the underlying
grammar. We also show how grammatical
constraints on the derivation sequence
can easily be integrated inside the RNNbased
sequential predictor. Our experiments
show important improvements over
previous results for the same dataset, and
also demonstrate the advantage of incorporating
the grammatical constraints.
Report number: