When & Where
Tuesdays & Thursdays, 2-3:20pm in SBSG 2200
Instructors
Lisa Pearl, Department of Cognitive Sciences, SBSG 2314
Office Hours for Lisa: Tuesday 11:30am - 1:00pm, and by appointment.
Email is the best way to reach her to schedule an appointment
not during regular office hours.
Mark Steyvers, Department of Cognitive Sciences, SBSG 2316
Office Hours for Mark: By appointment.
Email is the best way to reach him to schedule an appointment.
In this class, we will discuss a variety of papers that use computational models to investigate questions related to language learning. A bibliography of these articles can be found in the readings section, and all articles can be accessed through the schedule page (provided you have the class username and password). Topics to be discussed include:
- Computational models of language learning/acquisition:
Language is an amazingly complex system of knowledge that must be learned from noisy input. That very young children who don't have the cognitive sophistication to count to four can accomplish this task is no small wonder. That adults who have far more cognitive resources and learning strategies - not to mention knowledge of their native language - can't is perhaps even more striking. How is this possible? - Principles underlying models of language learning and change:
These include discussions of fundamental assumptions (e.g., analysis by synthesis), processes underlying linguistic development, the relationship between language acquisition and language change, and processes of linguistic evolution.
- Computational learning theory:
This includes formal representations of learnability, with particular interest in connections to language acquisition by humans. - Modeling information extraction from language by humans:
Humans have an amazing ability to extract all kinds of information from language text, including direct information such as content and indirect information such as sentiment, attitude, emotion, and intention. Since the only information available is the language, humans must be using linguistic cues to do so. What are these cues? Are there additional informative cues available, besides the ones humans naturally use? How good (or bad) are humans at noticing various linguistic cues?
Announcements:
All readings can be accessed using the username and password received in the first class session. (Email Lisa to get it.) Of course, you can also always track down these articles yourself in most cases. Look to the schedule, and be thinking about what papers/topics you'd like to present to the class.