Pregled bibliografske jedinice broj: 1085608
Meaning as Use: From Wittgenstein to Google’s Word2vec
Meaning as Use: From Wittgenstein to Google’s Word2vec // Guide to Deep Learning Basics / Skansi, Sandro (ur.)., 2020. str. 41-53 doi:10.1007/978-3-030-37591-1_5
CROSBI ID: 1085608 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Meaning as Use: From Wittgenstein to Google’s
Word2vec
Autori
Skelac, Ines ; Jandrić, Andrej
Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni
Knjiga
Guide to Deep Learning Basics
Urednik/ci
Skansi, Sandro
Izdavač
Springer
Godina
2020
Raspon stranica
41-53
ISBN
978-3-030-37591-1
Ključne riječi
Wittgenstein Firth Word2vec Machine translation Natural language processing
Sažetak
Modern natural language processing (NLP) systems are based on neural networks that learn concept representation directly from data. In such systems, concepts are represented by real number vectors, with the background idea that mapping words into vectors should take into account the context of their use. The idea is present in Wittgenstein’s both early and late works, as well as in contemporary general linguistics, especially in the works of Firth. In this article, we investigate the relevance of Wittgenstein’s and Firth’s ideas for the development of Word2vec, a word vector representation used in a machine translation model developed by Google. We argue that one of the chief differences between Wittgenstein’s and Firth’s approaches to the word meaning, compared to the one applied in Word2vec, lies in the fact that, although all of them emphasise the importance of context, its scope is differently understood.
Izvorni jezik
Engleski
Znanstvena područja
Filozofija
