About: Cross-lingual dependency transfer with harmonized Indian language treebanks

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

About: Cross-lingual dependency transfer with harmonized Indian language treebanks 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://tlt13.sfs.uni-tuebingen.de/tlt13-proceedings.pdf
Description	One of the most important aspect of cross-lingual dependency transfer is how different annotation styles which often underestimate the parsing accuracy are handled. The emerging trend is that the annotation style of different language treebanks can be harmonized into one style and the cumbersome manual transformation rules thus can be avoided. In this paper, we use harmonized treebanks (POS tagsets and dependency structures of original treebanks mapped to a common style) for inducing dependencies in a cross-lingual setting. We transfer dependencies using delexicalized parsers that use harmonized version of the original treebanks. We apply this approach to five Indian languages (Hindi, Urdu, Telugu, Bengali and Tamil) and show that best performance can be obtained in delexicalized parsing when the transfer takes place from Indian language (IL) to IL treebanks. One of the most important aspect of cross-lingual dependency transfer is how different annotation styles which often underestimate the parsing accuracy are handled. The emerging trend is that the annotation style of different language treebanks can be harmonized into one style and the cumbersome manual transformation rules thus can be avoided. In this paper, we use harmonized treebanks (POS tagsets and dependency structures of original treebanks mapped to a common style) for inducing dependencies in a cross-lingual setting. We transfer dependencies using delexicalized parsers that use harmonized version of the original treebanks. We apply this approach to five Indian languages (Hindi, Urdu, Telugu, Bengali and Tamil) and show that best performance can be obtained in delexicalized parsing when the transfer takes place from Indian language (IL) to IL treebanks. (en)
Title	Cross-lingual dependency transfer with harmonized Indian language treebanks Cross-lingual dependency transfer with harmonized Indian language treebanks (en)
skos:prefLabel	Cross-lingual dependency transfer with harmonized Indian language treebanks Cross-lingual dependency transfer with harmonized Indian language treebanks (en)
skos:notation	RIV/00216208:11320/14:10289406!RIV15-MSM-11320___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(LM2010013)
http://linked.open...vai/riv/dodaniDat	2015
http://linked.open...aciTvurceVysledku	Žabokrtský, Zdeněk Ramasamy, Loganathan
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	9253
http://linked.open...ai/riv/idVysledku	RIV/00216208:11320/14:10289406
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	treebanks; language; indian; harmonized; with; transfer; dependency; lingual; cross (en)
http://linked.open.../riv/klicoveSlovo	treebanks language cross dependency with transfer lingual harmonized indian
http://linked.open...ontrolniKodProRIV	[BD43976F2906]
http://linked.open...v/mistoKonaniAkce	Tübingen, Germany
http://linked.open...i/riv/mistoVydani	Tübingen, Germany
http://linked.open...i/riv/nazevZdroje	Proceedings of 13th International Workshop on Treebanks and Linguistic Theories (TLT13)
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...vavai/riv/projekt	LINDAT-CLARIN: Institute for analysis, processing and distribution of linguistic data
http://linked.open...UplatneniVysledku	2014
http://linked.open...iv/tvurceVysledku	Žabokrtský, Zdeněk Ramasamy, Loganathan
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2014-12-12 (xsd:date)
number of pages	12 (xsd:int)
http://purl.org/ne...btex#hasPublisher	University of Tübingen
https://schema.org/isbn	978-3-9809183-9-8
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, 30 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software