Naslov
XLike: Cross-lingual Knowledge Extraction

Autori
Tadić, Marko

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
Proceedings of the 17th Annual Conference of the European Association for Machine Translation / Tadić, Marko ; Koehn, Philipp ; Roturier, Johann ; Way, Andy - Zagreb : Hrvatsko društvo za jezične tehnologije / Croatian Language Technologies Society, 2014, 131-131

ISBN
978-953-55375-3-3

Skup
17th Annual Conference of the European Association for Machine Translation (EAMT2014)

Mjesto i datum
Dubrovnik, Hrvatska, 16.06.2014. - 18.06.2014

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Machine Translation; cross-lingual processing; knowledge extraction; semantic web; linked open data

Sažetak
The goal of the XLike project is to develop technology to monitor and aggregate knowledge that is currently spread across mainstream and social media, and to enable cross-lingual services for publishers, media monitoring and business intelligence. The aim is to combine scientific insights from several scientific areas to contribute in the area of cross-lingual text understanding. By combining modern computational linguistics, machine translation, machine learning, text mining and semantic technologies we plan to deal with the following two key open research problems: (1) to extract and integrate formal knowledge from multilingual texts with cross-lingual knowledge bases, and ; (2) to adapt linguistic techniques and crowdsourcing to deal with irregularities in informal language used primarily in social media. The developed technology will be language-agnostic, while within the project we specifically address English, German, Spanish, Chinese as major world languages and Catalan, Slovenian and Croatian as minority languages.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti, Filologija

POVEZANOST RADA