Next Article in Journal
A Node Localization Algorithm for Wireless Sensor Networks Based on Virtual Partition and Distance Correction
Next Article in Special Issue
Goal-Driven Visual Question Generation from Radiology Images
Previous Article in Journal
Detecting Cyber Attacks in Smart Grids Using Semi-Supervised Anomaly Detection and Deep Representation Learning
Previous Article in Special Issue
Pre-Training on Mixed Data for Low-Resource Neural Machine Translation
Article

Semantic Systematicity in Connectionist Language Production

1
Department of Language Science and Technology, Saarland University, 66123 Saarbrücken, Germany
2
Applied Cognitive Science Lab, The Pennsylvania State University, State College, PA 16802, USA
*
Author to whom correspondence should be addressed.
This paper is an extended version of our paper published in Calvillo, J., Brouwer, H., and Crocker, M.W. Connectionist Semantic Systematicity in Language Production. In Proceedings of the 38th Annual Conference of the Cognitive Science Society, Austin, TX, USA, 10–13 August 2016.
Academic Editor: Willy Susilo
Information 2021, 12(8), 329; https://doi.org/10.3390/info12080329
Received: 14 July 2021 / Revised: 6 August 2021 / Accepted: 10 August 2021 / Published: 16 August 2021
(This article belongs to the Special Issue Neural Natural Language Generation)
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. View Full-Text
Keywords: systematicity; compositionality; compositional generalization; deep learning; semantics; neural networks; sentence production; language production; language generation; generalization systematicity; compositionality; compositional generalization; deep learning; semantics; neural networks; sentence production; language production; language generation; generalization
Show Figures

Figure 1

MDPI and ACS Style

Calvillo, J.; Brouwer, H.; Crocker, M.W. Semantic Systematicity in Connectionist Language Production. Information 2021, 12, 329. https://doi.org/10.3390/info12080329

AMA Style

Calvillo J, Brouwer H, Crocker MW. Semantic Systematicity in Connectionist Language Production. Information. 2021; 12(8):329. https://doi.org/10.3390/info12080329

Chicago/Turabian Style

Calvillo, Jesús, Harm Brouwer, and Matthew W. Crocker 2021. "Semantic Systematicity in Connectionist Language Production" Information 12, no. 8: 329. https://doi.org/10.3390/info12080329

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop