RT conferenceObject
T1 Parsing as reduction
A1 Fernández González, Daniel
A1 Martins, Andre F. T
A2 Association for Computational Linguistics
K1 1203.17 Informática
AB We reduce phrase-representation parsing to dependency parsing. Our reduction is grounded on a new intermediate representation, “head-ordered dependency trees,” shown to be isomorphic to constituent trees. By encoding order information in the dependency labels, we show that any off-the-shelf, trainable dependency parser can be used to produce constituents. When this parser is non-projective, we can perform discontinuous parsing in a very natural manner. Despite the simplicity of our approach, experiments show that the resulting parsers are on par with strong baselines, such as the Berkeley parser for English and the best single system in the SPMRL-2014 shared task. Results are particularly striking for discontinuous parsing of German, where we surpass the current state of the art by a wide margin.
SN 9781941643723
YR 2015
FD 2015
LK http://hdl.handle.net/11093/6687
UL http://hdl.handle.net/11093/6687
LA eng
NO Ministerio de Ciencia e Innovación | Ref. TIN2010-18552-C03-01
DS Investigo
RD 10-sep-2024