On Chomsky and the Two Cultures of Statistical Learning

69 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Assessing gender bias in machine translation: a case study with Google Translate (2018, background): “Chomsky and Norvig’s debate (Norvig, 2017) is a microcosm of the two leading stand-points about the future of science in the face of increasingly sophisticated statistical models.”
On the Gap between Adoption and Understanding in NLP (2021, background): “Norvig (2017) has remarked on the tension be-tween rationalism, which wants models that can be understood, and empiricism, which wants models that work.”
Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Data (2020, background): “Rule-based approaches are criticized for being impossible to scale to the full complexity of real language data, providing good coverage of “standard” phenomena but requiring prohibitive additional to model the numerous special cases and exceptions that characterize human language (Norvig, 2017).”