This software is available in the Treehouse. You can also install it on your home machines, but you'll need to be running linux. If you don't already have a linux machine, we suggest KNOPPIX+LKB.
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 discussion sessions. We will cover the implementation of constraints in morphology, syntax and semantics within a unification-based lexicalist framework of grammar. 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, typically assigned on Mondays and due by Friday night. Course time on Wednesdays will be used for discussion of the exercises, so please work on them ahead of time and bring questions. Lab exercises will require write-ups to explain the phenomena as manifested in your language and how you implemented your analysis. Active class participation will be viewed favorably when it comes to grading.
Everyone will complete Lab 1 individually, but students may be expected to work in pairs starting with Lab 2, depending on the size of the class. Partners will alternate doing the write up portion of the lab, and have the grades for the labs where they did the write up weighted more heavily in their final course grade.
Lab exercises are to be turned in via Catalyst CollectIt
All course recordings will be posted on our common view page. If I'm slow to make them available there, please ping me over GoPost.
|4/1, 4/3||Overview, Introduction
|Lab 1: Getting to know the LKB and the Grammar Matrix; Choose language||Due: 4/5||Ch 1-3|
|4/8, 4/10||Testsuites, [incr tsdb()]||Lab 2: Testsuites/customization I: Word order, person/number/gender, pronouns, case, the rest of the NP, basic lexicon (full form)||Due: 4/12||Ch 4, 5|
(Optional: Oepen & Flickinger 1998)
|4/15, 4/17||The Grammar Matrix: Motivations, technical details
Morphotactics in the Grammar Matrix
|Lab 3: Testsuites/customization II: Tense/aspect, agreement, other required affixes, negation, argument optionality, demonstratives,||Due: 4/19||Bender, Flickinger & Oepen 2002; Goodman 2013|
|4/22, 4/24||Minimal Recursion Semantics
|Lab 4: Testsuites/customization III: Matrix yes-no questions, coordination, modification, non-verbal predicates, embedded clauses, information structure; test corpora||Due: 4/26||Copestake, Flickinger, Pollard, and Sag, 2005 (esp. Sec 3)|
Song and Bender 2012
|4/29, 5/1||Modification, Discourse Status, Argument Optionality; Precision grammars and corpus data||Lab 5: Test corpus, modification, demonstratives, argument optionality||Due: 5/3||Borthen and Haugereid 2005, available through UW Library's Electronic Journals (Research on Language and Computation 3(2):221-246)|
(Optional: Baldwin et al 2005)
|5/6, 5/8||Clause types, illocutionary force, non-verbal predicates||Lab 6: Polar questions, embedded clauses, non-verbal predicates||Due: 5/10|
|5/13, 5/15||Negation, raising, control, argument composition||Lab 7: I can eat glass. It doesn't hurt me.||Due: 5/17|
|5/20, 5/22||VPM, Getting started with MT||Lab 8: VPM, One more corpus sentence, First translation||Due: 5/24|
(No class 5/27)
|The LOGON MT architecture||Lab 9: Grammar clean up; Transfer rules||Due: 5/31||Oepen et al 2007|
|6/3, 6/5||The Grammar Matrix: Future directions||Machine Translation Extravaganza|