About: Multilingual Dependency Parsing: Using Machine Translated Texts instead of Parallel Corpora

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

About: Multilingual Dependency Parsing: Using Machine Translated Texts instead of Parallel Corpora 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
Description	This paper revisits the projection-based approach to dependency grammar induction task. Traditional cross-lingual dependency induction tasks one way or the other, depend on the existence of bitexts or target language tools such as part-of-speech (POS) taggers to obtain reasonable parsing accuracy. In this paper, we transfer dependency parsers using only approximate resources, i.e., machine translated bitexts instead of manually created bitexts. We do this by obtaining the the source side of the text from a machine translation (MT) system and then apply transfer approaches to induce parser for the target languages. We further reduce the need for the availability of labeled target language resources by using unsupervised target tagger. We show that our approach consistently outperforms unsupervised parsers by a bigger margin (8.2% absolute), and results in similar performance when compared with delexicalized transfer parsers. This paper revisits the projection-based approach to dependency grammar induction task. Traditional cross-lingual dependency induction tasks one way or the other, depend on the existence of bitexts or target language tools such as part-of-speech (POS) taggers to obtain reasonable parsing accuracy. In this paper, we transfer dependency parsers using only approximate resources, i.e., machine translated bitexts instead of manually created bitexts. We do this by obtaining the the source side of the text from a machine translation (MT) system and then apply transfer approaches to induce parser for the target languages. We further reduce the need for the availability of labeled target language resources by using unsupervised target tagger. We show that our approach consistently outperforms unsupervised parsers by a bigger margin (8.2% absolute), and results in similar performance when compared with delexicalized transfer parsers. (en)
Title	Multilingual Dependency Parsing: Using Machine Translated Texts instead of Parallel Corpora Multilingual Dependency Parsing: Using Machine Translated Texts instead of Parallel Corpora (en)
skos:prefLabel	Multilingual Dependency Parsing: Using Machine Translated Texts instead of Parallel Corpora Multilingual Dependency Parsing: Using Machine Translated Texts instead of Parallel Corpora (en)
skos:notation	RIV/00216208:11320/14:10289240!RIV15-MSM-11320___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(GP14-06548P), P(LM2010013)
http://linked.open...iv/cisloPeriodika	1
http://linked.open...vai/riv/dodaniDat	2015
http://linked.open...aciTvurceVysledku	Žabokrtský, Zdeněk Mareček, David Ramasamy, Loganathan
http://linked.open.../riv/druhVysledku	J - Článek v odborném periodiku
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	31033
http://linked.open...ai/riv/idVysledku	RIV/00216208:11320/14:10289240
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	corpora; parallel; instead; texts; translated; machine; using; parsing; dependency; multilingual (en)
http://linked.open.../riv/klicoveSlovo	corpora using texts multilingual dependency parsing instead machine parallel translated
http://linked.open...odStatuVydavatele	CZ - Česká republika
http://linked.open...ontrolniKodProRIV	[24648141CB7F]
http://linked.open...i/riv/nazevZdroje	The Prague Bulletin of Mathematical Linguistics
http://linked.open...in/vavai/riv/obor	AI
http://linked.open...ichTvurcuVysledku	3 (xsd:int)
http://linked.open...cetTvurcuVysledku	3 (xsd:int)
http://linked.open...vavai/riv/projekt	LINDAT-CLARIN: Institute for analysis, processing and distribution of linguistic data Sentence structure induction without annotated corpora
http://linked.open...UplatneniVysledku	2014
http://linked.open...v/svazekPeriodika	102
http://linked.open...iv/tvurceVysledku	Mareček, David Žabokrtský, Zdeněk Ramasamy, Loganathan
issn	0032-6585
number of pages	12 (xsd:int)
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, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software