CSC 485/2501 -- Introduction to Computational Linguistics

Fall 2023


Index of this document


Contact information

Instructor: Gerald Penn
Office: Vestibule outside MP 134/7
Office hours: MW 11am-12pm, or by appointment
Tel: (416)978-7390
Email: gpenn@teach.cs.utoronto.ca
Back to the index

Meeting times

Lectures:
Course Section Time Room
CSC 485 LEC 0101 MWF 10-11 MP 134 (except W: MP 137)
CSC 485 LEC 0201 MWF 12-1 ES B149
CSC 485 LEC 2001 MWF 10-11 MP 134 (except W: MP 137)
CSC 2501 LEC 0101 MWF 12-1 ES B149
Note: there will occasionally be tutorials on lecture days
Assignment/Tutor
Assignment Due Tutor
1 6th October Zhewei Sun
2 3rd November Jinman Zhao
3 7th December Ken Shi

A bulletin board has also been created for the class, which will be monitored by the TAs.

Back to the index

Texts for the Course

Required D. Jurafsky & J. Martin, Speech and Language Processing, Prentice Hall, 2nd ed., 2009.
See also the draft 3rd edition
Errata
Required S. Bird, E. Klein and E. Loper, Natural Language Processing with Python, O'Reilly, 2009. 
Recommended Martelli, Ravenscroft, Holden and McGuire.  Python in a Nutshell, 4th ed., O'Reilly, 2023.
Optional J. Allen,   Natural Language Understanding, 2nd ed., Pearson, 1994.
Recommended D. Mertz,  Text Processing in Python, Addison Wesley, 2003.
Free! various tutorials on the Python website

Reading for the Essays

Essay Due Date Title Author Publication Details
1 18th September Computing Machinery and Intelligence A. Turing Mind 59, 1950, pp. 433-460.
2 29th September Computational Complexity of Probabilistic Disambiguation K. Sima'an Grammars 5, 2002, pp. 125-151.
3 13th October
Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison
Similar but not the Same: Word Sense Disambiguation Improves Event Detection via Neural Representation Matching
A. Raganato, J. Camacho-Collados and R. Navigli
W. Lu and T. H. Nguyen
Proc. EACL, 2017, pp. 99-110.
Proc. EMNLP, 2018, pp. 4822-4828.
4 30th October
Monotonicity Marking from Universal Dependency Trees
NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning
Z. Chen and Q. Gao
Z. Chen, Q. Gao and L. S. Moss
Proc. IWCS, 2021, pp. 121-131.
Proc. *SEM, 2021, pp. 78-88.
5 24th November Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules H. Lee et al. Computational Linguistics 39(4), 2013, pp. 885-916

 

Readings for Lectures

Date Topic Reading
8-15 Sept Introduction to computational linguistics J&M: 1; BK&L: 1, 2.3, 4 as necessary
15-22 Sept Grammars and parsing J&M: 5.0-1, 12.0-12.3.5, 12.3.7, 12.7-12.7.1, 13.1, 13.2; BK&L: 8.0-8.5
25-29 Sept Lexical semantics J&M: 19.1-5, 20.8
2-6 Oct Word sense disambiguation J&M: 20.1-5
5-12 Oct Language modelling
16-18 Oct Chart parsing J&M: 13.3-4; A: 3.4, 3.6: BK&L: 8.4 and online extra section 8.2
20 Oct Ambiguity resolution
23-27 Oct Typed feature structures J&M: 12.3.4-6, 15.0-3; A: 4.1-5; BK&L: 9
30 Oct-3 Nov Attachment disambiguation
13-17 Nov Stochastic grammars J&M: 5.2-5.5.2, 5.6, 12.4, 14.0-1, 14.3-7
20-22 Nov Categorial grammars
22-24 Nov Supertagging
27-29 Nov Dependency graphs
1-4 Dec Question answering
6 Dec Anaphora resolution J&M: 21.0, 21.2-8
7 Dec Parsing for FWO languages

J&M: Jurafsky and Martin; BK&L: Bird, Klein and Loper; A = Allen; italics indicate additional reading.

Back to the index


Tentative Course outline

Back to the index

Calendar of important course-related events

Date Event
Fri, 8th September First lecture
Mon, 18th September Essay 1 due (CSC 2501)
Wed, 20th September Last day to add course (CSC 485/2501)
Fri, 29th September Essay 2 due (CSC 2501)
Fri, 6th October Assignment 1 due
Mon, 9th October Thanksgiving -- no meeting
Fri, 13th October Essay 3 due (CSC 2501)
Mon, 30th October Essay 4 due (CSC 2501)
Fri, 3rd November Assignment 2 due
6th-10th November Reading Week - no meetings
Mon, 6th November Last day to drop course (CSC 485/2501)
Fri, 24th November Essay 5 due (CSC 2501)
Thu, 7th December Last lecture
Thu, 7th December Assignment 3 due

Back to the index


Evaluation and related policies

There will be three homeworks and no final exam. For CSC 2501 students, there will also be 5 essays to write based upon assigned readings.
Component CSC 485 CSC 2501
Essay 1 3%
Essay 2 3%
Assignment 1 30% 25%
Essay 3 3%
Essay 4 3%
Assignment 2 30% 25%
Essay 5 3%
Assignment 3 30% 25%
Quizzes/Attendance 10% 10%
Important note on homeworks: No late homeworks will be accepted except in case of documented medical or other emergencies.

Policy on collaboration: Collaboration on and discussion of quiz content is encouraged. No collaboration on homeworks or essays is permitted.  The work you submit must be your own.  No student is permitted to discuss the homeworks with any other student from either this or previous years unless the instructor or TAs make the solutions publicly available.  Failure to observe this policy is an academic offense, carrying a  penalty ranging from a zero on the homework to suspension from the university.

Back to the index


Announcements

In this space, you will find announcements related to the course. Please check this space at least weekly. Back to the index

Handouts

In this space you will find on-line PDF versions of course handouts, including homeworks.

To view these handouts you will need access to a PDF viewer. If your machine does not have the required software, you can download Adobe Acrobat Reader for free.

Back to the index

Gerald Penn, 2nd December, 2023
This web-page was adapted from the web-page for another course, created by Vassos Hadzilacos.