Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Bjarke Felbo"'
Publikováno v:
NAACL-HLT (1)
Scopus-Elsevier
Scopus-Elsevier
Research in the area of style transfer for text is currently bottlenecked by a lack of standard evaluation practices. This paper aims to alleviate this issue by experimentally identifying best practices with a Yelp sentiment dataset. We specify three
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::943e972ef3e38850abcb7a450165c01c
http://arxiv.org/abs/1904.02295
http://arxiv.org/abs/1904.02295
Publikováno v:
CoNLL
Simple reference games are of central theoretical and empirical importance in the study of situated language use. Although language provides rich, compositional truth-conditional semantics to facilitate reference, speakers and listeners may sometimes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f69fa12004d41cfe9e9416e190fde61c
http://arxiv.org/abs/1810.03717
http://arxiv.org/abs/1810.03717
Autor:
Abhimanyu Dubey, Manuel Cebrian, Casey Jisoo Hong, Nick Obradovich, Ziv Epstein, Blakeley H. Payne, Matthew Groh, Iyad Rahwan, Bjarke Felbo, Judy Hanwen Shen
Publikováno v:
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18)
Scopus-Elsevier
IJCAI
Scopus-Elsevier
IJCAI
We introduce TuringBox, a platform to democratize the study of AI. On one side of the platform, AI contributors upload existing and novel algorithms to be studied scientifically by others. On the other side, AI examiners develop and post machine inte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::950499df15200e013e42a15554650763
https://hdl.handle.net/21.11116/0000-0003-1A4C-C21.11116/0000-0003-3F57-6
https://hdl.handle.net/21.11116/0000-0003-1A4C-C21.11116/0000-0003-3F57-6
Publikováno v:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Copenhagen, Denmark, September 7–11, 2017
arXiv
EMNLP
arXiv
EMNLP
NLP tasks are often limited by scarcity of manually annotated data. In social media sentiment analysis and related tasks, researchers have therefore used binarized emoticons and specific hashtags as forms of distant supervision. Our paper shows that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b7f22d04824ad1224f49d6ab8da62e58
http://arxiv.org/abs/1708.00524
http://arxiv.org/abs/1708.00524
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783319712727
ECML/PKDD (3)
ECML/PKDD (3)
Mobile phone metadata is increasingly used for humanitarian purposes in developing countries as traditional data is scarce. Basic demographic information is however often absent from mobile phone datasets, limiting the operational impact of the datas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb16c40c0328f0ac1bb43d27b3ae892b
https://doi.org/10.1007/978-3-319-71273-4_12
https://doi.org/10.1007/978-3-319-71273-4_12