CSCI 544 - Applied Natural Language Processing

Spring 2015
Kenji Sagae

Latest Announcements

[April 26, 2015] Updated project description to include individual reports about the work of other teams, as discussed in class. Each student must turn in an individual two to three page report summarizing the projects of ten other teams. The summaries must be based on the poster presentations.
[April 20, 2015] Project presentations (posters) will be held at MHP 101. Do not come to SAL for class next week!
[April 20, 2015] Project presentation schedule: Odd-numbered teams on Monday (4/27), Even-numbered teams on Wednesday (4/29). Find your team number here.
[April 8, 2015] Everyone should be working on class projects

Time:

MW 3:30pm-4:50pm

Location:

SAL 101

Instructor:

Kenji Sagae
Office hours: Wednesday 2:30-3:30pm PHE 514
or by appointment

Teaching Assistant:

Justin Garten
Office hours: Tuesday 5:00-7:00pm Leavey (LVL17)

Goals:

This course covers both fundamental and cutting-edge topics in Natural Language Processing (NLP) and provides students with hands-on experience in NLP applications.

Audience:

This graduate course is intended for:

students who want to understand current NLP technologies
students interested in building NLP applications
students interested in applications of NLP like sentiment analysis, dialogue systems, question answering systems, among others

Prerequisities:

Proficiency in programming, algorithms and data structures, basic knowledge of linear algebra and machine learning.

Related Courses

This course is part of USC's curriculum in natural language processing. There is a sister course, CSCI 662 Advanced Natural Language Processing, offered in the Fall semester, which covers complementary (and advanced) material and is intended for PhD students (or students who want to continue to a PhD program).

Coursework:

Students will work with real datasets and will build their own language processing, text classification and sentiment analysis systems. Grades will be based on:

Programming assignments (4 x 15%): the grades will depend on the performance of a system and a technical report.
Research project (40%), groups of three students, graded individually: 30% of the grade will depend on the project's relevance to the course, degree of difficulty, amount of work, correcness and written report, and 10% will depend on a written report about projects from other groups
Quizzes (1% extra-credit each): quizzes will be administered at the beginning of class with no advance notice. The questions will be straightforward. These are purely extra-credit and can only help your grade.

Homework and Project Guidelines

Homework 0
Homework 1
Homework 2
Homework 3
Project

Spring 2015 Schedule

Date	Instructor	Lecture
January 12	Sagae	Introduction and basic concepts
January 14	Sagae	Text Classification (Naive Bayes) Reading: Manning, Raghavan and Schutze, Introduction to information retrieval, Chapter 13
January 19	MLK Holiday
January 21	Sagae	More classification (Perceptron) Reading: Hal Daume III, A course in machine learning, Chapter 3
January 26	Sagae	Sequence labeling (perceptron, POS tagging)
January 28	Sagae	Part-of-speech tagging Reading: Ratnaparkhi, A maximum entropy model for part-of-speech tagging
February 2	Sagae	Shallow Parsing, NER and NLP tools Reading: Sha and Pereira, Shallow parsing with conditional random fields Tjong Kim Sang and Buchholz, Introduction to the CoNLL-2000 Shared Task: Chunking Tjong Kim Sang, Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition
February 4	Sagae	Parsing
February 9	Sagae	Parsing
February 11	Sagae	PCFG Reading: Charniak (1997), Statistical Techniques for Natural Language Parsing Reading: Mark Johnson (1998), PCFG models of linguistic tree representations
February 16	President's Day
February 18	Sagae	Shift-Reduce Parsing, Dependency Parsing Nivre (2008), Algorithms for deterministic incremental dependency parsing Sagae and Lavie (2005), A classifier-based parser with linear run-time complexity
February 23	Sagae	Semantic Role Labeling Reading: Gildea and Palmer (2002), The necessity of parsing for predicate argument recognition Propbank information CoNLL shared tasks on dependency-based semantic role labeling: 2008 and 2009
February 25	Sagae	Language Modeling Reading: Chen & Goodman (1998) An Empirical Study of Smoothing Techniques for Language Modeling Links to LM toolkits: OpenGRM SRI Language Modeling Toolkit
March 2	Sagae	Speech Acts Reading: Stolcke et al. (2000) Dialogue act modeling for automatic tagging and recognition of conversational speech
March 4	Sagae	Named Entity Recognition revisited, Information Extraction
March 9	Sagae	Named Entity Discrimination
March 11	Sagae	Class project discussion, clustering Manning, Raghavan and Schütze, Introduction to Information Retrieval, Chapter 15 (flat clustering) and Chapter 16 (hierarchical clustering).
March 16	Spring Break
March 18	Spring Break
March 23	Sagae	Word classes, knowledge representation
March 25	Sagae	Knowledge and information extraction
March 30	Sagae	Discourse
April 1	Sagae	Domain adaptation
April 6	Sagae	Domain adaptation II McClosky, Charniak and Johnson. Automatic Domain Adaptation for Parsing. NAACL 2010. Daume III. Frustratingly easy domain adaptation. ACL 2007.
April 8	Garten	Distributed word representations
April 13	Sagae	NLP for Social Media, review
April 15	Sagae	NLP applications
April 20	Georgila	Speech Synthesis
April 22	Sagae	Wrap up, the road ahead
April 27	Class Presentations (MPH 101)
April 29	Class Presentations (MPH 101)

Setup guides

Statement for Students with Disabilities:

Any student requesting academic accommodations based on a disability is required to register with Disability Services and Programs (DSP) each semester. A letter of verification for approved accommodations can be obtained from DSP. Please be sure the letter is delivered to me (or to TA) as early in the semester as possible. DSP is located in STU 301 and is open 8:30 a.m.-5:00 p.m., Monday through Friday. The phone number for DSP is (213) 740-0776.

Statement on Academic Integrity:

USC seeks to maintain an optimal learning environment. General principles of academic honesty include the concept of respect for the intellectual property of others, the expectation that individual work will be submitted unless otherwise allowed by an instructor, and the obligations both to protect one's own academic work from misuse by others as well as to avoid using another's work as one's own. All students are expected to understand and abide by these principles. Scampus, the Student Guidebook, contains the Student Conduct Code in Section 11.00, while the recommended sanctions are located in Appendix A: http://www.usc.edu/dept/publications/SCAMPUS/gov/. Students will be referred to the Office of Student Judicial Affairs and Community Standards for further review, should there be any suspicion of academic dishonesty. The Review process can be found at: http://www.usc.edu/student-affairs/SJACS/.