Show simple item record

dc.contributor.author
Gastaldi, Juan Luis
dc.date.accessioned
2021-03-29T10:32:30Z
dc.date.available
2020-12-11T13:49:20Z
dc.date.available
2020-12-11T14:10:25Z
dc.date.available
2020-12-14T07:19:08Z
dc.date.available
2021-03-11T09:58:52Z
dc.date.available
2021-03-29T10:32:30Z
dc.date.issued
2021-03
dc.identifier.issn
2210-5433
dc.identifier.issn
2210-5441
dc.identifier.other
10.1007/s13347-020-00393-9
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/456052
dc.description.abstract
The present paper intends to draw the conception of language implied in the technique of word embeddings that supported the recent development of deep neural network models in computational linguistics. After a preliminary presentation of the basic functioning of elementary artificial neural networks, we introduce the motivations and capabilities of word embeddings through one of its pioneering models, word2vec. To assess the remarkable results of the latter, we inspect the nature of its underlying mechanisms, which have been characterized as the implicit factorization of a word-context matrix. We then discuss the ordinary association of the “distributional hypothesis” with a “use theory of meaning,” often justifying the theoretical basis of word embeddings, and contrast them to the theory of meaning stemming from those mechanisms through the lens of matrix models (such as vector space models and distributional semantic models). Finally, we trace back the principles of their possible consistency through Harris’s original distributionalism up to the structuralist conception of language of Saussure and Hjelmslev. Other than giving access to the technical literature and state of the art in the field of natural language processing to non-specialist readers, the paper seeks to reveal the conceptual and philosophical stakes involved in the recent application of new neural network techniques to the computational treatment of language.
en_US
dc.language.iso
en
en_US
dc.publisher
Springer
en_US
dc.subject
Word embeddings
en_US
dc.subject
Natural language processing
en_US
dc.subject
Word2vec
en_US
dc.subject
Neural networks
en_US
dc.subject
Philosophy of language
en_US
dc.subject
Matrix models
en_US
dc.subject
Distributional hypothesis
en_US
dc.subject
Structuralism
en_US
dc.title
Why Can Computers Understand Natural Language?
en_US
dc.type
Journal Article
dc.date.published
2020-05-14
ethz.title.subtitle
The Structuralist Image of Language Behind Word Embeddings
en_US
ethz.journal.title
Philosophy & Technology
ethz.journal.volume
34
en_US
ethz.journal.issue
1
en_US
ethz.pages.start
149
en_US
ethz.pages.end
214
en_US
ethz.grant
Towards a theory of mathematical signs based on the automatic treatment of mathematical corpora
en_US
ethz.identifier.scopus
ethz.publication.place
Dordrecht
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02045 - Dep. Geistes-, Sozial- u. Staatswiss. / Dep. of Humanities, Social and Pol.Sc.::09591 - Wagner, Roy / Wagner, Roy
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02045 - Dep. Geistes-, Sozial- u. Staatswiss. / Dep. of Humanities, Social and Pol.Sc.::09591 - Wagner, Roy / Wagner, Roy
en_US
ethz.grant.agreementno
839730
ethz.grant.agreementno
839730
ethz.grant.fundername
EC
ethz.grant.fundername
EC
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.program
H2020
ethz.grant.program
H2020
ethz.date.deposited
2020-12-11T13:49:34Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2020-12-14T07:19:18Z
ethz.rosetta.lastUpdated
2022-03-29T06:05:29Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Why%20Can%20Computers%20Understand%20Natural%20Language?&rft.jtitle=Philosophy%20&%20Technology&rft.date=2021-03&rft.volume=34&rft.issue=1&rft.spage=149&rft.epage=214&rft.issn=2210-5433&2210-5441&rft.au=Gastaldi,%20Juan%20Luis&rft.genre=article&rft_id=info:doi/10.1007/s13347-020-00393-9&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record