Natural language processing (NLP) enables computers to make use of data represented in human language (including the vast quantities of data available on the web) and to interact with computers on human terms. Applications from machine translation to speech recognition and web-based information retrieval demand both precision and robustness from NLP technology. Meetings these demands will require better hand-built grammars of human languages combined with sophisticated statistical processing methods. This class focuses on the implementation of linguistic grammars, drawing on a combination of sound grammatical theory and engineering skills.
Class meetings will alternate between lectures and hands-on lab sessions. We will cover the implementation of constraints in morphology, syntax and semantics within a unification-based lexicalist framework of grammar. The weekly exercises will focus on building up an implemented grammar for a language of your choice (everyone must work on a different language, so be prepared to work with a language you don't know well!), based on the LinGO Grammar Matrix. At the end of the quarter, we will use the various grammars in a machine translation task.
Prerequisites: Linguistics 566 or equivalent. No programming experience is required.
Note: To request academic accommodations due to a disability, please contact Disabled Student Services, 448 Schmitz, 206-543-8924 (V/TTY). If you have a letter from Disabled Student Services indicating that you have a disability which requires academic accommodations, please present the letter to the instructor so we can discuss the accommodations you might need in this class.
Weekly lab exercises, begun in class on Wednesdays (lab) and turned in by Sunday night. (I'd make the deadline Friday, but would rather not spend the weekend grading things...) Most lab exercises will require write-ups to explain the phenomena as manifested in your language and how you implemented your analysis. You will be advised on Mondays of what data or information about your language you need to bring for Wednesday. Active class participation will be viewed favorably when it comes to grading.
Lab exercises are to be turned in via Catalyst E-Submit:
|Dates||Lecture||Lab prep||Lab||Due date||Reading|
The Grammar Matrix
|Prep 1: Emacs tutorial||Lab 1: Getting to know the LKB||Due: 4/1||Ch 1-3|
|4/4, 4/6||Formalism, A tour of the Matrix||Prep 2||Lab 2: Word order, small vocabulary, lexical semantics||Due: 4/8||Ch 4-5|
|4/11, 4/13||Using [incr tsdb()]
Matrix tour cont
|Prep 3||Lab 3: Running testsuites, case and agreement||Due: 4/15||Oepen & Flickinger 1998|
|4/18, 4/20||Optional arguments, Minimal Recursion Semantics||Prep 4||Class cancelled: sorry!||Due: --||Copestake, Flickinger, Pollard, and Sag, to appear|
|4/25, 4/27||Minimal Recursion Semantics, cont||Prep 5||Lab 4: Argument optionality and Modification||Due: 4/29|
|5/2, 5/4||Precision grammars and corpus data; messages and clausal semantics||Prep 6||Lab 5: Clausal semantics (declaratives)||Due: 5/6||Baldwin et al 2005|
|5/9, 5/11||Stump the chump (quick presentation of problems from each language; suggestions on how they might be handled)||Prep 7||Lab 6: Polar questions, imperatives||Due: 5/13|
|5/16, 5/18||Raising, control, argument composition, sentential negation||Prep 8||Lab 7: I can eat glass. It doesn't hurt me.||Due: 5/20|
|5/23, 5/25||Guest Lecture: Scott Drellishak on Coordination||Prep 9||Lab 8: Coordination||Due: 5/27||Drellishak and Bender 2005|
|5/30, 6/1||Holiday, no class||Prep 10||Machine Translation Extravaganza||Nope|