A survey on training and evaluation of word embeddings

Autor: Guillaume Gravier, Nihel Kooli, Robin Allesiardo, François Torregrossa, Vincent Claveau

Publikováno v: International Journal of Data Science and Analytics
International Journal of Data Science and Analytics, Springer Verlag, 2021, 11 (2), pp.85-103. ⟨10.1007/s41060-021-00242-8⟩
International Journal of Data Science and Analytics, 2021, 11 (2), pp.85-103. ⟨10.1007/s41060-021-00242-8⟩

International audience; Word Embeddings have proven to be effective for many Natural Language Processing tasks by providing word representations integrating prior knowledge. In this article, we focus on the algorithms and models used to compute those

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7301a886ce62d3f070714a5e1991cf1b
https://hal.archives-ouvertes.fr/hal-03148517/document

How We Achieved a Production Ready Slot Filling Deep Neural Network Without Initial Natural Language Data

Autor: Nihel Kooli, Robin Allesiardo, Erwan Pigneul, François Torregrossa

Publikováno v: Communications in Computer and Information Science ISBN: 9783030368074
ICONIP (4)

Training deep networks requires large volumes of data. However, for many companies developing new products, those data may not be available and public data-sets may not be adapted to their particular use-case. In this paper, we explain how we achieve

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::181b61cee5ead07f2565cbf12fa53bea
https://doi.org/10.1007/978-3-030-36808-1_27