Learning multilingual topics from incomparable corpora
Multilingual topic models enable crosslingual tasks by extracting consistent topics from
multilingual corpora. Most models require parallel or comparable training corpora, which …
multilingual corpora. Most models require parallel or comparable training corpora, which …
Scalable cross-lingual document similarity through language-specific concept hierarchies
C Badenes-Olmedo, JL Redondo-García… - Proceedings of the 10th …, 2019 - dl.acm.org
With the ongoing growth in number of digital articles in a wider set of languages and the
expanding use of different languages, we need annotation methods that enable browsing …
expanding use of different languages, we need annotation methods that enable browsing …
Learning multilingual topics from incomparable corpus
Multilingual topic models enable crosslingual tasks by extracting consistent topics from
multilingual corpora. Most models require parallel or comparable training corpora, which …
multilingual corpora. Most models require parallel or comparable training corpora, which …
The CLIN30 shared task: Have-doubling in historical varieties of Dutch
M Schraagen, J Wall, E Brito - Computational Linguistics in the …, 2020 - clinjournal.org
Abstract The CLIN30 Shared Task is defined as a computational approach to classify have-
doubling, which is a syntactic phenomenon combining a past participle construction with an …
doubling, which is a syntactic phenomenon combining a past participle construction with an …
Semantically-enabled Browsing of Large Multilingual Document Collections
C Badenes-Olmedo - 2021 - oa.upm.es
Searching for similar documents and exploring the major themes are common activities
when browsing document collections. With the ongoing growth in the number of digital …
when browsing document collections. With the ongoing growth in the number of digital …