After taking this course, the students will be able to
- describe, characterize and compare probabilistic and structural frameworks for representing language;
- characterize and discuss the relationship between the language representation frameworks and the cognitive processes involved in various aspects of language acquisition (such as word learning or speech segmentation);
- evaluate and analyze computational models of language learning.
The final grade of the course will be based on two related assignments (40%) and a final written exam (60%).
We will discuss using formal models for studying human language learning. In the first part of the course, we will focus on the high-level objectives of studying human language, the general properties of computational models of language learning, and the most common frameworks for developing them. In the second half of the course, we will focus on the cognitive processes involved in human language acquisition including speech segmentation, the association of words to meanings, learning language structure, and formation of linguistic categories, and analyze a number of computational models of each of these aspects.