A case for deep learning in semantics
Response to Pater
Dados Bibliográficos
| ID | 11111863 |
|---|---|
| Autores | Christopher Potts (0000-0002-7978-6055, autor correspondente) |
| Ano | 2019 |
| Volume | 95 |
| Fascículo | 1 |
| Páginas | e115-e124 |
| Data de publicação | 2019-01-01 |
| Peer Reviewed | Sim |
| Open Access | Sim |
| Tipo | ARTICLE |
| Periódico | Language (JOURNAL) |
| Identificadores do periódico | ISSN: 0097-8507 • E-ISSN: 1535-0665 |
| Editora | Project MUSE (PUBLISHER • US) |
| DOI | 10.1353/lan.2019.0019 |
| OpenAlex | W2915765757 |
| Idioma | EN |
| Citações recebidas | 1 |
| Referências citadas | 14 |
Pater's (2019) target article builds a persuasive case for establishing stronger ties between theoretical linguistics and connectionism (deep learning). This commentary extends his arguments to semantics, focusing in particular on issues of learning, compositionality, and lexical meaning
Artificial neural network · Cognition · Cognitive linguistics · Cognitive science · Connectionism · Construction Grammar · Epistemology · Lexical item · Lexical Semantics · Linguistics · Meaning (existential) · Natural language processing · Principle of compositionality · Programming language · Semantics (computer science) · Artificial Intelligence · Computer Science · Language, Metaphor, and Cognition · Natural Language Processing Techniques · Philosophy · Psychology · Syntax, Semantics, Linguistic Variation
A unitary approach to Lexical Pragmatics
Composition in Distributional Models of Semantics
From Frequency to Meaning
The Handbook of Contemporary Semantic Theory
Approximation by superpositions of a sigmoidal function
Deep learning
Studies in linguistic semantics.
Semantics from Different Points of View
Finding Structure in Time
Bringing Machine Learning and Compositional Semantics Together
Computational Linguistics and Deep Learning
Dogmas of understanding
Distributional Models of Word Meaning
Generative linguistics and neural networks at 60
| Obras citantes distintas | 1 |
|---|---|
| Citações por ano | 0,2 |
| Intervalo de citações | 2021 - 2021 (1) |
| Velocidade de citação | historical |
| Altamente citado | Não |