Improving Dependency Parsing Using Sentence Clause Charts

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F16%3A10335482" target="_blank" >RIV/00216208:11320/16:10335482 - isvavai.cz</a>

Výsledek na webu

<a href="http://acl2016.org/files/acl-srw-2016.pdf" target="_blank" >http://acl2016.org/files/acl-srw-2016.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Improving Dependency Parsing Using Sentence Clause Charts

Popis výsledku v původním jazyce

We propose a method for improving the dependency parsing of complex sentences. This method assumes segmentation of input sentences into clauses and does not require to re-train a parser of one's choice. We represent a sentence clause structure using clause charts that provide a layer of embedding for each clause in the sentence. Then we formulate a parsing strategy as a two-stage process where (i) coordinaed and subordinated clauses of the sentence are parsed separately with respect to the sentence clause chart and (ii) their dependency trees become subtrees of the final tree of the sentence. The object language is Czech and the parser used is a maximum spanning tree parser trained on the Prague Dependency Treebank. We have achieved an average 0.97% improvement in the unlabeled attachment score. Although the method has been designed for the dependency parsing of Czech, it is useful for other parsing techniques and languages.

Název v anglickém jazyce

Improving Dependency Parsing Using Sentence Clause Charts

Popis výsledku anglicky

We propose a method for improving the dependency parsing of complex sentences. This method assumes segmentation of input sentences into clauses and does not require to re-train a parser of one's choice. We represent a sentence clause structure using clause charts that provide a layer of embedding for each clause in the sentence. Then we formulate a parsing strategy as a two-stage process where (i) coordinaed and subordinated clauses of the sentence are parsed separately with respect to the sentence clause chart and (ii) their dependency trees become subtrees of the final tree of the sentence. The object language is Czech and the parser used is a maximum spanning tree parser trained on the Prague Dependency Treebank. We have achieved an average 0.97% improvement in the unlabeled attachment score. Although the method has been designed for the dependency parsing of Czech, it is useful for other parsing techniques and languages.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics - Student Research Workshop

ISBN

978-1-945626-02-9

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

86-92

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Berlin, Germany

Datum konání akce

7. 8. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—