About: Hybrid Combination of Constituency and Dependency Trees into an Ensemble Dependency Parser

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Hybrid Combination of Constituency and Dependency Trees into an Ensemble Dependency Parser Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
rdfs:seeAlso	http://www.aclweb.org/anthology/W/W12/W12-0503
Description	Dependency parsing has made many advancements in recent years, in particular for English. There are a few dependency parsers that achieve comparable accuracy scores with each other but with very different types of errors. This paper examines creating a new dependency structure through ensemble learning using a hybrid of the outputs of various parsers. We combine all tree outputs into a weighted edge graph, using 4 weighting mechanisms. The weighted edge graph is the input into our ensemble system and is a hybrid of very different parsing techniques (constituent parsers, transition-based dependency parsers, and a graph-based parser). From this graph we take a maximum spanning tree. We examine the new dependency structure in terms of accuracy and errors on individual part-of-speech values. The results indicate that using a greater number of more varied parsers will improve accuracy results. The combined ensemble system, using 5 parsers based on 3 different parsing techniques, achieves an accuracy score Dependency parsing has made many advancements in recent years, in particular for English. There are a few dependency parsers that achieve comparable accuracy scores with each other but with very different types of errors. This paper examines creating a new dependency structure through ensemble learning using a hybrid of the outputs of various parsers. We combine all tree outputs into a weighted edge graph, using 4 weighting mechanisms. The weighted edge graph is the input into our ensemble system and is a hybrid of very different parsing techniques (constituent parsers, transition-based dependency parsers, and a graph-based parser). From this graph we take a maximum spanning tree. We examine the new dependency structure in terms of accuracy and errors on individual part-of-speech values. The results indicate that using a greater number of more varied parsers will improve accuracy results. The combined ensemble system, using 5 parsers based on 3 different parsing techniques, achieves an accuracy score (en)
Title	Hybrid Combination of Constituency and Dependency Trees into an Ensemble Dependency Parser Hybrid Combination of Constituency and Dependency Trees into an Ensemble Dependency Parser (en)
skos:prefLabel	Hybrid Combination of Constituency and Dependency Trees into an Ensemble Dependency Parser Hybrid Combination of Constituency and Dependency Trees into an Ensemble Dependency Parser (en)
skos:notation	RIV/00216208:11320/12:10130050!RIV13-MSM-11320___
http://linked.open...avai/riv/aktivita	R
http://linked.open...avai/riv/aktivity	R
http://linked.open...vai/riv/dodaniDat	2013
http://linked.open...aciTvurceVysledku	Žabokrtský, Zdeněk Green, Nathan David
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	Univerzita Karlova v Praze / Matematicko-fyzikální fakulta
http://linked.open...dnocenehoVysledku	139939
http://linked.open...ai/riv/idVysledku	RIV/00216208:11320/12:10130050
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	parser; dependency; ensemble; into; trees; dependency; constituency; combination; hybrid (en)
http://linked.open.../riv/klicoveSlovo	hybrid ensemble into dependency trees parser constituency combination
http://linked.open...ontrolniKodProRIV	[02FE4FE587AB]
http://linked.open...v/mistoKonaniAkce	Avignon, France
http://linked.open...i/riv/mistoVydani	Avignon, France
http://linked.open...i/riv/nazevZdroje	Proceedings of the Workshop on Innovative Hybrid Approaches to the Processing of Textual Data
http://linked.open...in/vavai/riv/obor	IN
http://linked.open...ichTvurcuVysledku	2 (xsd:int)
http://linked.open...cetTvurcuVysledku	2 (xsd:int)
http://linked.open...UplatneniVysledku	2012
http://linked.open...iv/tvurceVysledku	Žabokrtský, Zdeněk Green, Nathan David
http://linked.open...vavai/riv/typAkce	CST - Celostátní
http://linked.open.../riv/zahajeniAkce	2012-04-23 (xsd:date)
number of pages	8 (xsd:int)
http://purl.org/ne...btex#hasPublisher	Association for Computational Linguistics
https://schema.org/isbn	978-1-937284-19-0
http://localhost/t...ganizacniJednotka	11320

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 25 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software