Parsing as Reduction

被引：0

作者：

Fernandez-Gonzalez, Daniel ^{[1
]}

Martins, Andre F. T. ^{[2
,3
]}

机构：

[1] Univ Vigo, Dept Informrat, Campus As Lagoas, Orense 32004, Spain

[2] Inst Super Tecn, Inst Telecomunicacoes, P-1049001 Lisbon, Portugal

[3] Priberam Labs, P-1000123 Lisbon, Portugal

来源：

PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 | 2015年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We reduce phrase-based 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-theshelf, 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 non-reranking 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.

引用

页码：1523 / 1533

页数：11