9 citations · 12 across the 4 of their papers we have counts for
5 papers
Construction Grammar and Language Models
Harish Tayyar Madabushi, Laurence Romain, Petar Milin +1
Recent progress in deep learning and natural language processing has given rise to powerful models that are primarily trained on a cloze-like task and show some evidence of having…
Abstraction not Memory: BERT and the English Article System
Harish Tayyar Madabushi, Dagmar Divjak, Petar Milin
Article prediction is a task that has long defied accurate linguistic description. As such, this task is ideally suited to evaluate models on their ability to emulate native-speake…
A learning perspective on the emergence of abstractions: the curious case of phonemes
Petar Milin, Benjamin V. Tucker, Dagmar Divjak
In the present paper we use a range of modeling techniques to investigate whether an abstract phone could emerge from exposure to speech sounds. In effect, the study represents an…
CxGBERT: BERT meets Construction Grammar
Harish Tayyar Madabushi, Laurence Romain, Dagmar Divjak +1
While lexico-semantic elements no doubt capture a large amount of linguistic information, it has been argued that they do not capture all information contained in text. This assump…
Keeping it simple: Implementation and performance of the proto-principle of adaptation and learning in the language sciences
Petar Milin, Harish Tayyar Madabushi, Michael Croucher +1
In this paper we present the Widrow-Hoff rule and its applications to language data. After contextualizing the rule historically and placing it in the chain of neurally inspired ar…