Sie können Bookmarks mittels Listen verwalten, loggen Sie sich dafür bitte in Ihr SLUB Benutzerkonto ein.
Medientyp:
E-Artikel
Titel:
Towards a Universal Semantic Dictionary
Beteiligte:
Castro-Bleda, Maria Jose;
Iklódi, Eszter;
Recski, Gábor;
Borbély, Gábor
Erschienen:
MDPI AG, 2019
Erschienen in:
Applied Sciences, 9 (2019) 19, Seite 4060
Sprache:
Englisch
DOI:
10.3390/app9194060
ISSN:
2076-3417
Entstehung:
Anmerkungen:
Beschreibung:
A novel method for finding linear mappings among word embeddings for several languages, taking as pivot a shared, multilingual embedding space, is proposed in this paper. Previous approaches learned translation matrices between two specific languages, while this method learns translation matrices between a given language and a shared, multilingual space. The system was first trained on bilingual, and later on multilingual corpora as well. In the first case, two different training data were applied: Dinu’s English–Italian benchmark data, and English–Italian translation pairs extracted from the PanLex database. In the second case, only the PanLex database was used. The system performs on English–Italian languages with the best setting significantly better than the baseline system given by Mikolov, and it provides a comparable performance with more sophisticated systems. Exploiting the richness of the PanLex database, the proposed method makes it possible to learn linear mappings among an arbitrary number of languages.