Alexander Clark and Shalom Lappin
LSA Summer Institute 2011,
University of Colorado, Boulder, Colorado
July 7-August 1, 2011
Determining the nature of the language faculty has always
been one of the central problems in linguistic theory. Is this faculty a rich
set of powerful domain specific constraints on language acquisition, or does it
consist of weak initialization biases for domain general learning procedures?
The key debates on this question turn on learnability
considerations, where these are formulated as versions of the "argument
from the poverty of the stimulus" (APS). This discussion continues to play
a major role in shaping the field.
This course comprises a series of lectures that address this question from a
variety of perspectives. We analyze the APS in its various forms, and we
consider how it supports linguistic nativism. We
focus on formal versions of the APS which derive their force from the
computational hardness of the language learning task. We see how these
arguments can be made more precise within both traditional and modern learning
paradigms. In the second half of the course we pursue a constructive reply to
the APS by offering solutions to the learnability
challenges that it presents. We show how some of the ideas and methods of
distributional learning (which have their origin in the work of structuralist linguists) provide the basis for developing
provably correct procedures that learn complex, richly structured language
classes. The course is based on our recent monograph
Alexander
Clark and Shalom Lappin (2011), Linguistic Nativism and the Poverty of the
Stimulus, Wiley-Blackwell.
Overview: Nativism and the Argument from the Poverty of the Stimulus
Reading: Chapters 1 and 2 in Clark and Lappin (2011)
Formal Models of Learning
Reading: Chapter 4, pp. 70-81
Identification in the Limit
Reading: Rest of Chapter 4
Probabilistic Learning
Reading: Chapter 5 and 6
Complexity and Efficient Learning
Reading: Chapter 7
Distributional Learning
Reading: Chapter 8 (and some new material)
Advanced Topics in Distributional Learning
new material
Distributional Approaches to Meaning
new material