Computer Science 248/448

Statistical Speech and Language Processing

Fall 2013

Instructor: Dan Gildea (Office hours: Wed 2:00-3:00pm or by appointment CSB 730)
TA: Yuncheng Li (Office hours: Thu 2:00-3:00pm or by appointment CSB 617, Availability at homepage)
Location: Tu/Th 3:25-4:40pm, CSB 703.

Homeworks

Text: Jurafsky and Martin, Speech and Language Processing, 2nd edition.

  • We will have a short python help session in CSB 703 at 12:45 on Friday 9/6.

Syllabus

Onwe will coverwhich means that after class you will understandif before class you have read
9/3 Perceptron for Tagging NLP = ML + DP Collins 2002
9/5 Hidden Markov Models viterbi, forward JM 6
9/10 Variational Bayes digamma, expected log probs JM 5; Johnson 2007
9/12 CRFs f - E[f] McCallum 2001
9/17 N-grams Good-Turing, Katz, Kneser-Ney JM 4
9/19 Signal Processing for Speech MFCC JM 9
9/24 Forced Alignment Deep learning Hinton 2012
9/26 Large Vocabulary Speech Recognition beam search, multistack decoding JM 10
10/1 Max Margin Learning subgradients Tsochantaridis 2004, Ratliff 2006
10/3 Context Free Grammars highest prob string, infinite trees JM 13
10/8 Fall Break
10/10 Treebanks right node raising JM 12
10/15 Parsing cyk, earley, posterior decoding, inside-outside JM 14
10/17 Real-World Parsing lexicalization, markovization, reranking JM 15; Charniak 2005
10/22 Discriminative Methods tree CRF, early update perceptron Finkel 08, Huang 2012
10/24 Review
10/29 Midterm
10/31 Midterm Solutions
11/5 Semantics lambda calculus Zettlemoyer 2005
11/7 Machine Translation source-channel, model 1 JM 25
11/12 Machine Translation model 2, 3, hmm Brown 1993
11/14 Machine Translation decoding Koehn et al. 2003
11/19 Machine Translation syntax-based MT Yamada & Knight 2001
11/21 Machine Translation syntax-based decoding Galley 2004, chiang 05
11/26 Machine Translation what's in a translation rule Och 2004
12/3 Machine Translation Parameter Optimization Och 2003
12/5 Sentiment Analysis Liang 2011, Pang 2004
12/10 Lexical Semantics JM 20, Lin 1998, Mihacea 2007
12/12 Review come to class with questions!
Final Exam: Fri 12/20, 8:30-11:30am, CSB 703.

Grading

  • Final exam: 35%
  • Homeworks: 35%
  • Midterm: 25%
  • Class participation: 5%
  • No late homework
  • Programming assignments must be in python, and must run on class account
  • Lecture notes must be in latex, and must compile on class account. See latex template.
  • Lecture notes for Tu are due 3:25pm Th, notes for Th are due 3:25pm Mon
gildea @ cs rochester edu
December 3, 2013