TY - CHAP
T1 - Deep learning and vector space model
AU - Sidorov, Grigori
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2019.
PY - 2019
Y1 - 2019
N2 - In recent years, a novel paradigm appeared related to application of neural networks to any tasks related to artificial intelligence [59], in particular, in natural language processing [39]. It became extremely popular in NLP area after works of Mikolov et al. starting in 2013 [74, 75]. The main idea of this paradigm is to apply neural networks for automatic learning of relevant features with various levels of generalization in vector space model. Sometimes this model of representation of objects is called continuous vector space model. In general, this paradigm is called “deep learning.”.
AB - In recent years, a novel paradigm appeared related to application of neural networks to any tasks related to artificial intelligence [59], in particular, in natural language processing [39]. It became extremely popular in NLP area after works of Mikolov et al. starting in 2013 [74, 75]. The main idea of this paradigm is to apply neural networks for automatic learning of relevant features with various levels of generalization in vector space model. Sometimes this model of representation of objects is called continuous vector space model. In general, this paradigm is called “deep learning.”.
UR - http://www.scopus.com/inward/record.url?scp=85064717510&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-14771-6_7
DO - 10.1007/978-3-030-14771-6_7
M3 - Capítulo
AN - SCOPUS:85064717510
T3 - SpringerBriefs in Computer Science
SP - 41
EP - 43
BT - SpringerBriefs in Computer Science
PB - Springer
ER -