Fr. 90.00

Computational Construction Grammar - A Usage-Based Approach

Englisch · Fester Einband

Versand in der Regel in 3 bis 5 Wochen

Beschreibung

Mehr lesen










This Element introduces a usage-based computational approach to Construction Grammar that draws on techniques from natural language processing and unsupervised machine learning. This work explores how to represent constructions, how to learn constructions from a corpus, and how to arrange the constructions in a grammar as a network. From a theoretical perspective, this Element examines how construction grammars emerge from usage alone as complex systems, with slot-constraints learned at the same time that constructions are learned. From a practical perspective, this work is accompanied by a Python package which enables linguists to incorporate construction grammars into their own corpus-based work. The computational experiments in this Element are important for testing the learnability, variability, and confirmability of Construction Grammar as a theory of language. All code examples will leverage the cloud computing platform Code Ocean to guide readers through implementation of these algorithms.

Inhaltsverzeichnis

1. Representing constructions; 2. Learning constructions; 3. Forming the constructicon; 4. Conclusions; References.

Zusammenfassung

This Element introduces a usage-based computational approach to Construction Grammar that draws on techniques from natural language processing and unsupervised machine learning. The computational experiments are important for testing the learnability, variability, and confirmability of Construction Grammar as a theory of language.

Kundenrezensionen

Zu diesem Artikel wurden noch keine Rezensionen verfasst. Schreibe die erste Bewertung und sei anderen Benutzern bei der Kaufentscheidung behilflich.

Schreibe eine Rezension

Top oder Flop? Schreibe deine eigene Rezension.

Für Mitteilungen an CeDe.ch kannst du das Kontaktformular benutzen.

Die mit * markierten Eingabefelder müssen zwingend ausgefüllt werden.

Mit dem Absenden dieses Formulars erklärst du dich mit unseren Datenschutzbestimmungen einverstanden.