Interpretability of Hungarian embedding spaces using a knowledge base

Balogh Vanda and Berend Gábor and Diochnos Dimitrios I. and Turán György and Farkas Richárd: Interpretability of Hungarian embedding spaces using a knowledge base.

[thumbnail of kdslakfes.pdf]
Preview
Cikk, tanulmány, mű
kdslakfes.pdf

Download (491kB) | Preview

Abstract

While word embeddings have proven to be highly useful in many NLP tasks, they are difficult to interpret for humans. Sparse word embeddings are reminiscent of knowledge bases containing words that are already characterized in sparse forms. In our work, we investigate to what extent sparse word representations convey knowledge about the words in knowledge bases. We utilize Hungarian sparse word embeddings and ConceptNet, a knowledge base that supports Hungarian.

Item Type: Conference or Workshop Item
Journal or Publication Title: Magyar Számítógépes Nyelvészeti Konferencia
Date: 2019
Volume: 15
ISBN: 978-963-315-393-2
Page Range: pp. 48-62
Event Title: Magyar Számítógépes Nyelvészeti Konferencia (15.) (2019) (Szeged)
Related URLs: http://acta.bibl.u-szeged.hu/58556/
Uncontrolled Keywords: Nyelvészet - számítógép alkalmazása
Additional Information: Bibliogr.: p. 61-62. ; összefoglalás angol nyelven
Date Deposited: 2019. Jul. 03. 11:39
Last Modified: 2022. Nov. 08. 11:49
URI: http://acta.bibl.u-szeged.hu/id/eprint/59073

Actions (login required)

View Item View Item