Computer Science 248/448

Statistical Speech and Language Processing

Fall 2019

Instructor: Dan Gildea (Office hours: Mon 2:00-3:00pm, Thu 2:00-3:00pm)
TA: Wasif Chowdhury
Location: Tu/Th 11:05am-12:20pm, Gavet 312.

Homeworks

Recommended resources:

Syllabus

Onwe will coverwhich means that after class you will understandif before class you have read
8/29 Perceptron for Tagging NLP = ML + DP Collins 2002
9/3 Hidden Markov Models viterbi, forward JM 6
9/5 CRFs f - E[f] McCallum 2001
9/10 Max Margin Learning subgradients Tsochantaridis 2004, Ratliff 2006
9/12 EM for HMM JM 6
9/17 latent CRF
9/19 neural CRF
9/24 Context Free Grammars highest prob string, infinite trees JM 13
9/26 Context Free Grammars viterbi, inside-outside
10/1 Context Free Grammars viterbi, inside-outside
10/3 Parsing minimum risk decoding, neural parsing Finkel 08
10/8 Parsing em, latent crf, max-margin
10/10 Treebanks right node raising JM 12
10/15 Fall Break
10/17 Search beam search, A*
10/22 Dependency parsing
10/24 Review
10/29 Midterm
10/31 Midterm Solutions
11/5 Machine Translation model 1, 2, 3 Brown 1993
11/7 Machine Translation decoding Koehn et al. 2003 Galley 2004, Chiang 05
11/12 Neural Machine Translation LSTM Sutskever 2014, Bahdanau 2014
11/14 Machine Translation minimum risk training Papineni 2002, Shen 2016
11/19 Semantics word2vec Mikolov 2013, Pennington 2014
11/21 Semantics lambda calculus JM 20, Zettlemoyer 2005, Liang 2011
11/26Encoder Pretraining bert and elmo
12/3 Encoder pretraining
12/5 Something fun
12/10 Something fun
Final Exam: Thursday, December 19, 4-7pm, Gavet 312.

Grading

  • Final exam: 35%
  • Homeworks: 40%
  • Midterm: 25%
  • No late homework
  • Programming assignments must be in python, and must run on class account

gildea @ cs rochester edu
September 10, 2019