Please use this identifier to cite or link to this item: doi:10.22028/D291-34586
Title: Semantic Systematicity in Connectionist Language Production
Author(s): Calvillo, Jesús
Brouwer, Harm
Crocker, Matthew W.
Language: English
Title: Information
Volume: 12
Issue: 8
Publisher/Platform: MDPI
Year of Publication: 2021
Free key words: systematicity
compositional generalization
deep learning
neural networks
sentence production
language production
language generation
DDC notations: 100 Philosophy
Publikation type: Journal Article
Abstract: Decades of studies trying to define the extent to which artificial neural networks can exhibit systematicity suggest that systematicity can be achieved by connectionist models but not by default. Here we present a novel connectionist model of sentence production that employs rich situation model representations originally proposed for modeling systematicity in comprehension. The high performance of our model demonstrates that such representations are also well suited to model language production. Furthermore, the model can produce multiple novel sentences for previously unseen situations, including in a different voice (actives vs. passive) and with words in new syntactic roles, thus demonstrating semantic and syntactic generalization and arguably systematicity. Our results provide yet further evidence that such connectionist approaches can achieve systematicity, in production as well as comprehension. We propose our positive results to be a consequence of the regularities of the microworld from which the semantic representations are derived, which provides a sufficient structure from which the neural network can interpret novel inputs.
DOI of the first publication: 10.3390/info12080329
Link to this record: urn:nbn:de:bsz:291--ds-345867
ISSN: 2078-2489
Date of registration: 27-Aug-2021
Faculty: P - Philosophische Fakultät
Department: P - Sprachwissenschaft und Sprachtechnologie
Professorship: P - Prof. Dr. Matthew W. Crocker
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
File Description SizeFormat 
information-12-00329.pdf1,3 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons