Universal linguistic inductive biases via meta-learning
- Richard McCoy, Department of Cognitive Science, Johns Hopkins University, Baltimore, Maryland, United States
- Erin Grant, EECS Department, U.C. Berkeley, Berkeley, California, United States
- Paul Smolensky, Microsoft Research AI, Microsoft, Redmond, Washington, United States
- Tom Griffiths, Department of Psychology, Princeton University, Princeton, New Jersey, United States
- Tal Linzen, Department of Cognitive Science, Johns Hopkins University, Baltimore, Maryland, United States
AbstractHow do learners acquire languages from the limited data available to them? This process must involve some inductive biases—factors that affect how a learner generalizes—but it is unclear which inductive biases can explain observed patterns in language acquisition. To facilitate computational modeling aimed at addressing this question, we introduce a framework for giving particular linguistic inductive biases to a neural network model; such a model can then be used to empirically explore the effects of those inductive biases. This framework disentangles universal inductive biases, which are encoded in the initial values of a neural network’s parameters, from non-universal factors, which the neural network must learn from data in a given language. The initial state that encodes the inductive biases is found with meta-learning, a technique through which a model discovers how to acquire new languages more easily via exposure to many possible languages. By controlling the properties of the languages that are used during meta-learning, we can control the inductive biases that meta-learning imparts. We demonstrate this framework with a case study based on syllable structure. First, we specify the inductive biases that we intend to give our model, and then we translate those inductive biases into a space of languages from which a model can meta-learn. Finally, using existing analysis techniques, we verify that our approach has imparted the linguistic inductive biases that it was intended to impart.
Return to previous page