Cog Lunch: Steven Piantadosi "One model for the learning of language"
Description
Speaker: Professor Steven Piantadosi, UC Berkeley
(Note: Prof. Piantadosi will be on Zoom; in-person viewing and Q&A will be available in 46-6011.)
Title: One model for the learning of language
Significance:
It has long been hypothesized that language acquisition may be impossible without innate knowledge of the structures that occur in natural language. Here, we show that a domain general learning setup, originally developed in cognitive psychology to model rule learning, is able to acquire key pieces of natural language from relatively few examples of sentences. This develops a new approach to formalizing linguistic learning and highlights some features of language and language acquisition that may arise from general cognitive processes.
Abstract:
A major goal of linguistics and cognitive science is to understand what class of learning systems can acquire natural language. Until recently, the computational requirements of language have been used to argue that learning is impossible without a highly constrained hypothesis space. Here, we describe a learning system that is maximally unconstrained, operating over the space of all computations, and is able to acquire many of the key structures present in natural language from positive evidence alone. We demonstrate this by providing the same learning model with data from 74 distinct formal languages which have been argued to capture key features of language, have been studied in experimental work, or come from an interesting complexity class. The model is able to successfully induce the latent system generating the observed strings from small amounts of evidence in almost all cases, including for regular (e.g., an, (??)?(ab)n, and {?,?}+{a,b}+), context-free (e.g., ????,????+?anbn, anbn+m, and ???xxR), and context-sensitive (e.g., ??????,????????anbncn, anbmcndm, and xx) languages, as well as for many languages studied in learning experiments. These results show that relatively small amounts of positive evidence can support learning of rich classes of generative computations over structures. The model provides an idealized learning setup upon which additional cognitive constraints and biases can be formalized.