Emergence of Syntax Needs Minimal Supervision

Autor: Raphaël Bailly, Kata Gábor
Přispěvatelé: Statistique, Analyse et Modélisation Multidisciplinaire (SAmos-Marin Mersenne) (SAMM), Université Paris 1 Panthéon-Sorbonne (UP1), Équipe de Recherche en Textes, Informatique, Multilinguisme (ERTIM), Institut National des Langues et Civilisations Orientales (Inalco), Gabor, Kata
Rok vydání: 2020
Předmět:
FOS: Computer and information sciences
Computer science
02 engineering and technology
[INFO] Computer Science [cs]
computer.software_genre
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
030507 speech-language pathology & audiology
03 medical and health sciences
Meaning (philosophy of language)
Simple (abstract algebra)
0202 electrical engineering
electronic engineering
information engineering
[INFO]Computer Science [cs]
Structure (mathematical logic)
Computer Science - Computation and Language
Learnability
business.industry
Pragmatics
16. Peace & justice
Part of speech
Syntax
TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES
[INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL]
020201 artificial intelligence & image processing
Grammaticality
Artificial intelligence
0305 other medical science
business
computer
Computation and Language (cs.CL)
Natural language processing
Zdroj: ACL 2020
ACL 2020, Jul 2020, Seattle, United States
ACL
DOI: 10.48550/arxiv.2005.01119
Popis: This paper is a theoretical contribution to the debate on the learnability of syntax from a corpus without explicit syntax-specific guidance. Our approach originates in the observable structure of a corpus, which we use to define and isolate grammaticality (syntactic information) and meaning/pragmatics information. We describe the formal characteristics of an autonomous syntax and show that it becomes possible to search for syntax-based lexical categories with a simple optimization process, without any prior hypothesis on the form of the model.
Comment: ACL 2020
Databáze: OpenAIRE
Externí odkaz: