Journal
INFORMATION
Volume 12, Issue 8, Pages -Publisher
MDPI
DOI: 10.3390/info12080329
Keywords
systematicity; compositionality; compositional generalization; deep learning; semantics; neural networks; sentence production; language production; language generation; generalization
Categories
Funding
- Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) [232722074-SFB 1102]
- National Science Foundation [BCS-1734304]
- Mexican National Council of Science and Technology (CONACYT)
Ask authors/readers for more resources
Studies suggest that connectionist models can achieve systematicity, especially in language production. The new model proposed in the research can generate multiple new sentences in different situations, demonstrating semantic and syntactic generalization and arguably systematicity.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available