jungyeul / computational-tools-for-linguistic-analysis-ubc

Computational Tools for Linguistic Analysis

LING 242 Computational Tools for Linguistic Analysis

@UBC (Winter Term 2 2023/24)

schedule

date	description	course materials
2024		[syllabus]
Lecture 0	shell commands
		[Lecture 0 slides], [Lab 0 slides], [lab suppl - command lines in PC (Yadong)]
		[Assignment 0 (Due 11:59PM on Jan 25)] [Assignment 0 described (Jasbrina)]
Lecture 1	preprocessing
	sentence boundary detection	Suggested Readings: [Sentence Boundary Detection and the Problem with the U.S.] [Sentence Boundary Detection: A Long Solved Problem?]
	tokenization	Suggested Readings: [Tokenization: Returning to a Long Solved Problem]
		[Lecture 1 slides], [Lab 1 slides] [JP-algorithm (Junrui)]
		[Assignment 1 (Due 11:59PM on Feb 8)] [Assignment 1 described (Kiki)]
		[Assignment 1 in the class]
Lecture 2	lm
		Suggested Readings: [Chap. 3, N-gram Language Models], Speech and Language Processing (3rd ed. draft)
		[Lecture 2 slides], [Lab 2 slides]
		[Assignment 2 (Due 11:59PM on Feb 22)] [Assignment 2 described (Marcell)]
Lecture 3	pos tagging & sequence labeling algorithms
	morphosyntax tasks in nlp & hmm	Suggested Readings: [Chap. 8, Sequence Labeling for Parts of Speech and Named Entities], Speech and Language Processing (3rd ed. draft) [Chunking], CoNLL-2000 Shared Task [Language-Independent Named Entity Recognition], CoNLL-2003 Shared Task [Semantic Role Labeling], CoNLL-2004 and CoNLL-2005 Shared Tasks
		[Lecture 3 slides], [Lab 3 slides]
		[Assignment 3 (Due 11:59PM on March 7)] [Assignment 3 described (Andrew)]
Lecture 4	syntax
	parsing	Suggested Readings: [Chap. 12, Constituency Grammars], Speech and Language Processing (3rd ed. draft) [Chap. 13, Constituency Parsing] [Chap. 14, Dependency Parsing]
		[Lecture 4 slides], [Lab 4 slides]
		[ptb examples] [ptb ud examples] [CNF conversion]
		[Assignment 4 (Due 11:59PM on March 21)] [Assignment 4 described (Annabelle)]
Lecture 5	classification
		[Lecture 5 slides], [Lab 5 slides]
		[Assignment 5 (Due 11:59PM on April 4)] [Assignment 5 described (Leah)]
Lecture 6	morphology
	morphological segmentation	Suggested Readings: [Empirical Methods for Compound Splitting] [Morphological Segmentation Inside-Out] [Unsupervised Discovery of Morphemes]
	morphological paradigm	Suggested Readings: [Supervised Learning of Complete Morphological Paradigms]
		[Lecture 6 slides], [Lab 6 slides]
		[Assignment 6 (Due 11:59PM on April 20, no extension)] [Assignment 6 described (Maya)]
Lecture 7	machine translation
	document & word alignment
	smt & nmt
		[Lecture 7 slides]
		[Assignment 7 described (no submission)]
Lecture 8	semantics
		[Lecture 8 slides]
***	***

• [lecture] 9:30-10:45AM on Monday and Wednesday
• [lab] 10-11:30AM Friday (Bring Your Own Laptop)

office hours

• Jungyeul (Instructor): 6-7PM on Thursday (in-person [ORCH 4018], online [zoom]), (email: jungyeul at mail.ubc.ca)

reference materials

• Speech and Language Processing (3rd ed. draft) [link]