Measuring the impact of collocational knowledge on sentence parsing

 

Uloženo v:
Podrobná bibliografie
Autor: Wehrli, Eric
Médium: artículo original
Stav:Versión publicada
Datum vydání:2017
Popis:In this paper we focus on collocations, which have been studied in computational linguistics since they constitute a key factor when processing natural languages. For instance, they usually represent a challenge in automatic translation because the association of two terms is not easily computed. We proposed that the parser should be provided with a lexical database in order to make more effective the identification of collocations during the parsing process. We assessed this claim by using a corpus of 6’000 sentences retrieved from the British magazine The Economist Espresso. The corpus was parsed twice, first with the collocation detection component turned on and then with it turned off, and to make the comparison the Fips tagger was used. The results showed an improvement of the quality when the parser has access to collocation knowledge. 
Země:Portal de Revistas UCR
Instituce:Universidad de Costa Rica
Repositorio:Portal de Revistas UCR
Jazyk:Español
OAI Identifier:oai:portal.ucr.ac.cr:article/30225
On-line přístup:https://revistas.ucr.ac.cr/index.php/kanina/article/view/30225
Klíčové slovo:collocations
multiword expressions
sentence parsing
computational linguistics
natural language processing