Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Yoshinari Fujinuma"'
Autor:
Dasha Pruss, Yoshinari Fujinuma, Ashlynn R Daughton, Michael J Paul, Brad Arnot, Danielle Albers Szafir, Jordan Boyd-Graber
Publikováno v:
PLoS ONE, Vol 14, Iss 5, p e0216922 (2019)
This work examines Twitter discussion surrounding the 2015 outbreak of Zika, a virus that is most often mild but has been associated with serious birth defects and neurological syndromes. We introduce and analyze a collection of 3.9 million tweets me
Externí odkaz:
https://doaj.org/article/2912c455711749f2a7447df49eae057a
Autor:
Masato Hagiwara, Yoshinari Fujinuma
Publikováno v:
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15).
Readability or difficulty estimation of words and documents has been investigated independently in the literature, often assuming the existence of extensive annotated resources for the other. Motivated by our analysis showing that there is a recursiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7b27356a4035f56fce7c9af901ce970f
https://doi.org/10.18653/v1/2021.textgraphs-1.16
https://doi.org/10.18653/v1/2021.textgraphs-1.16
Publikováno v:
ACL
Cross-lingual word embeddings (CLWE) are often evaluated on bilingual lexicon induction (BLI). Recent CLWE methods use linear projections, which underfit the training dictionary, to generalize on BLI. However, underfitting can hinder generalization t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da47dcef3f363d570075074791210b42
https://doi.org/10.18653/v1/2020.acl-main.201
https://doi.org/10.18653/v1/2020.acl-main.201
Publikováno v:
ACL (1)
Cross-lingual word embeddings encode the meaning of words from different languages into a shared low-dimensional space. An important requirement for many downstream tasks is that word similarity should be independent of language - i.e., word vectors
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9aa3e135c27cb516040cd6e01f199fce
http://arxiv.org/abs/1906.01926
http://arxiv.org/abs/1906.01926
Publikováno v:
AAAI
Text classification must sometimes be applied in a low-resource language with no labeled training data. However, training data may be available in a related language. We investigate whether character-level knowledge transfer from a related language h
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::105cbbe505ced691468f4fc3827a546f