CSCI 544 Fall 2018 course page

Jonathan May and Nanyun (Violet) Peng

Lectures SAL 101, Wednesdays and Fridays 8:00-9:50 am
Instructor office hours Jonathan May or Nanyun (Violet) Peng, RTH 512, Wednesdays and Fridays 10-11am or 11am-12pm with appointment
Textbook None required; Speech and Language Processing, 2nd Edition1 is optional but badly out of date. The new version (called ``jm'' in reading selection notes below) is incomplete but preferred2. All required readings from jm and elsewhere will be listed in the syllabus.
TA Office hours Xusen Yin, 10:30am-12:30pm Mon., SAL Lab
Ramesh Manuvinakurike, 11:30am-1:30pm Wed., SAL Lab
Sarik Ghazarian, 3pm-5pm Wed., SAL Lab
Quizzes (3% of grade) approximately 25 x 0.12% of grade each. Multiple choice online tests taken mid-class to break up the monotony. Open note, open internet, open discussion.
Homeworks (48.6% of grade) 6 x 8.1% of grade each. A mix of programming and written assignments, electronic submission due 11:59 PM local Pacific time per table below.
Project (8.1% of grade) Can be done in groups of up to 4. Preliminary part due mid-class, due on last class day. (this may be replaced with a seventh homework)
Late days Four (4) cumulative with no more than two (2) per assignment. 50% penalty first day; thereafter, no credit afterward.
Midterm (15% or 25% of grade, whichever is more advantageous) Friday, October 5, 8:00-9:45 am. Covers lectures, readings, and homeworks from 8/22-10/3
Final exam (15% or 25% of grade, whichever is more advantageous) Wednesday, December 5, 8:00-10:00 am. Covers lectures, readings, and homeworks from 8/22-11/30 (i.e. the entire class)
Contact us On Piazza or in class/office hours. Please do not email (unless notified otherwise).

A note about the midterm/final grading: whichever you do better on will count as 25% of your grade and the other one will count as 15% of your grade. Together the tests will count as 40% of your grade.

Syllabus/schedule - subject to change - latest version is always on the website!

instructor date material reading HW out HW due
JM 8/22intro, applicationsjm v2 c1 3, hirschberg & manning 4
JM 8/24corpora, text processing, words, regular expressions (lec 2 starting code 5)NLTK ch.2 6, jmv3 c27, nathan schneider's notes 8, Unix for poets9, sculpting text10,HW 1 (due 9/7)
JM 8/29Morphology, Finite-State Automata, FSA relationship to regex, finite state transducers jm v2 c3 11
JM 8/31 probability Goldwater probability tutorial 12, HW 2 (due 9/14)
JM 9/5Classifiers, features, naive Bayes, perceptron, logistic regressionjm v3 c613, Eisenstein notes pp. 21-4814
JM 9/7pos tagging, hmm, search jm v3 c915, blunsom notes16, collins notes (optional, more detailed)17HW1
NP 9/12parsing and syntax 1: treebanks, evaluation, cky, grammar inductionpenn treebank 18, jm v3 c1219, jm v3 c1320HW3=project proposal (due 9/26)
NP 9/14parsing and syntax 2: pcfgs, restructuring, lexicalization, smoothing, beamingchiang notes21HW2
NP 9/19parsing and syntax 3: dependencies, mst and shift reduce algorithmsjm v3 c1422HW 4 (due 10/10)
NP 9/21ngram LMsjm v3 c423
NP 9/26smoothing, interpolation(optional) chen and goodman24HW 3(pp)
NP 9/28feed forward lm, rnn lmjm v3 c825
NP/JM (?) 10/3 REVIEW
NP 10/10classical lexical semantics jm v3 c1726 HW 4
NP 10/12distributional lexical semanticsjm v3 c1527, jm v3 c1628HW 5 (due 10/26)
NP 10/17RNNs, LM and semantics jmv3 c729 c930
NP 10/19Information Extraction jmv3 c2131HW 6 (due 11/9)
NP 10/24Information Extraction: CRF Collins's Note32 Sutton and McCallum'a Note33 project rewrite
NP 10/26Neural CRF Lample et. al.34HW 5
JM 10/31 MT evaluation and alignment arcturan and centauri35, Bleu36, TODO
JM 11/2Statistical MT Brown et al. 37 (mathy bits of models 3+ can be skimmed), Knight workbook38, mert39
JM 11/7Neural MT TODO
JM 11/9Summarization TODO HW 7 (due 11/30) HW 6
JM 11/14 Generation, Dialogue TODO
JM 11/16 Dialogue TODO
JM 11/28Applications TODO
JM/NP 11/30ReviewHW 7 & project


... Edition1
... preferred2
... c13
... manning4
... code5
... ch.26
... c27
... notes8
... poets9
... text10
... c311
... tutorial12
... c613
... 21-4814
... c915
... notes16
... detailed)17
... treebank18
... c1219
... c1320
... notes21
... c1422
... c423
... goodman24
... c825
... c1726
... c1527
... c1628
... c729
... c930
... c2131
... Note32
... Note33
... al.34
... centauri35
... Bleu36
... al.37
... workbook38
... mert39