6.864: Natural Language Processing

[main] | [general information] | [homeworks]

Announcements:

[11/6] Problem Set 4 has been released. Due date: November 20, 5pm.
[10/23] Project proposals are due 11/11. Project presentations will be held on 12/2 and 12/4.
[10/23] The second quiz will be held on the last day of classes -- 12/9.
[10/22] Problem set 3 has been released. Due date: Nov 4, 5pm.
[10/13] Links to previous years midterms: 2005 2006 Please note that these exams were given after covering certain topics that we haven't touched upon yet, so please ignore questions that mention things like HMM's, EM, Global linear models.
[10/13] Review session for the midterm at 5:30 pm on Tuesday Oct 14 in 32-G4 lounge. (go up the gates side elevators to the 4th floor and make a left).
[10/5] Liang Huang (University of Pennsylvania) will give a talk "Forest-Based Algorithms in Natural Language Processing" (October 7th, 3pm, 34-401A). If you are interested in parsing, please consider attending.
[10/1] Due date of Problem Set 2 changed from October 9 to October 10!
[9/27] Problem Set 2 has been released. Due date: October 10, 5pm.
[9/19] We will have our first midterm on October 16th.
[9/16] Regular TA office hours will be 2:30-3:20 on Thursdays in 32-362. In addition, Monday Sept 22 there will be an extra hour (or longer as needed) from 7pm-8pm.
[9/16] Corrected a typo in Problem Set 1, Problem 3 [ (c_{ij}) -> P(c_{ij} ]
[9/10] Problem Set 1 has been released. Due date: September 23, 5pm.
[9/4] Kevin Knight(USC) will give a talk "Language Translation as Code-Breaking" on September 17th. If you want to learn about state-of-the-art machine translation, consider attending this talk.

Date	Topic	References
9/4	Introduction and Overview	Lillian Lee I'm sorry Dave, I'm afraid I can't do that: Linguistics, Statistics, and Natural Language Processing circa 2001 To appear in the National Academies' study on the Fundamentals of Computer Science
9/9	Language Modeling	Jurafsky&Martin, chapter 4.
9/11	Language Modeling (cont.)	Additional Reading: Stanley F. Chen and Joshua T. Goodman "An Empirical Study of Smoothing Techniques for Language Modeling", Technical Report, Harvard University, 1998.
9/16	Morphology	Jurafsky&Martin, chapter 3.1 and 3.12. Rie Kubota Ando and Lillian Lee. "Mostly-Unsupervised Statistical Segmentation of Japanese: Applications to Kanji.", Proceedings of NAACL, 2000.
9/18	Morphology	M. Creutz "Unsupervised segmentation of words using prior distributions of morph length and frequency." , Proceedings of ACL, 2003. David Yarowsky, Grace Ngai, and Richard Wicentowski "Inducing Multilingual Text Analysis Tools via Robust Projection across Aligned Corpora." , Proceedings of HLT, 2001. (section 7 only)
9/23	Syntax: PCFGs	Jurafsky&Martin, chapter 12 and 13.
9/26	Syntax: Parsing	Michael Collins "Three Generative, Lexicalised Models for Statistical Parsing." , Proceedings of the ACL/EACL, 1997.
9/30	Syntax: Parsing (cont.)
10/2	Log-linear Models	Jurafsky&Martin, chapter 6.6 and 6.7.
10/7	Log-linear Models (cont.)	Jurafsky&Martin, chapter 6.6 and 6.7.
10/14	Tagging	Adwait Ratnaparkhi. 1996. A Maximum Entropy Part-Of-Speech Tagger. In Proceedings of the EMNLP.
10/16	Midterm
10/21	Midterm Solution
10/23	Perceptron	Michael Collins, Brian Roark, and Murat Saraclar. Discriminative Syntactic Language Modeling for Speech Recognition. , Proceedings of the ACL.
10/28	Collective Classification: Mincut	Bo Pang and Lillian Lee. 2004 A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts, Proceedings of the ACL.
10/30	Collective Classification: ILP	Regina Barzilay and Mirella Lapata. 2006. "Aggregation via Set Partitioning for Natural Language Generation", , Proceedings of the NAACL/HLT.
11/6	EM	Required Reading: Note on EM by Michael Collins.
11/13	EM
11/18	EM
11/18	Machine Translation (guest lecture by M. Collins)	Lecture Slides (note that slides 29-45 were not covered in detail)	11/25	Machine Translation (guest lecture by M. Collins)	Lecture Slides - Part 1 (slides 1-41 were covered) Lecture Slides - Part 2 (slides 1-20 were covered)