More and more of life is now manifested online, and many of the digital traces that are left by human activity are increasingly recorded in natural-language format. This research-oriented course examines the opportunities for natural language processing to contribute to the analysis and facilitation of socially embedded processes. Possible topics include analysis of online conversations, learning social-network structure, analysis of text in political or legal domains, review aggregation systems. CDNM's web page CDNM's web page

No tab selected

(If you're looking for anything other than lecture contents and have javascript enabled, click on the appropriate tab above.)

Prerequisites, course selection, enrollment

Prerequisites All of the following: CS 2110 or equivalent programming experience; a course in artificial intelligence or any relevant subfield (e.g., NLP, information retrieval, machine learning); proficiency with using machine learning tools (e.g., fluency at training an SVM, knowledge of how to assess a classifier’s performance using cross-validation)

Enrollment CS/IS PhD students may enroll online. Other students interested in adding the course, (wel)come to the first day of class. Enrollment questions will be addressed then, when we have a better sense of what the demand is and how many CS/IS PhD students are interested in taking the class.

Choosing among NLP courses: How do I know which one is right for me?

In 2016-2017, we are blessed with a plethora of NLP-related offerings!

At the graduate level:

For undergraduate courses on offer, consult the Cornell NLP course list.

For more information before classes begin The webpage of the previous running (Fall 2015) of this course gives a general idea of what the course will be like

Administrative info and overall course structure

Course homepage http://www.cs.cornell.edu/courses/cs6742/2016fa. Main site for course info, assignments, readings, lecture references, etc.; updated frequently.

CMS page http://cms.csuglab.cornell.edu. Site for submitting assignments, unless otherwise noted.

Piazza page http://piazza.com/cornell/Fall2016/cs6742 Course announcements and Q&A/discussion site. Social interaction and all that, you know.

Contacting the instructor

Overview of course schedule. Details subject to change. Full schedule is maintained on the main course webpage.

Lecture Agenda Pedagogical purpose Assignments
#1

Course overview

 

Pilot empirical study for a research idea based on readings provided.

#2 - #4

Lecture topics related to the A1 readings: Online reviews: individual expression, community dynamics; Online asynchronous conversations.

Case studies to explore some topics and research styles find interesting. Get-to-know-you exercises to get everyone familiar and comfortable with each other.

 
Next 6 meetings, not counting presentations or discussions

Lectures on, potentially, linguistic coordination, linguistic adaptation, influence, persuasion, diffusion, discourse structure, advanced language modeling

Foundational material

Potentially some assignments based on the lectures.

Next large block of meetings

Dicussion of proposed projects based on the readings

Practice with fast research-idea generation. Feedback as to what proposals are most interesting, most feasible, etc.

Discussion of student project proposals, based on the readings for that class meeting. Each class meeting thus involves everyone reading at least one of the two assigned papers and posting a new research proposal based on the reading to Piazza.

Thoughtfulness and creativity are most important to , but take feasibility into account.

Remainder of the course

Activities related to course projects

Development of a "full-blown" research project (although time restrictions may limit ambitions). For our purposes, "interesting" is more important than "thorough".

 

Some time in December (to be determined by the registrar): final project writeup due

Grading Of most interest to is productive research-oriented discussion participation (in class and on Piazza), interesting research proposals and pilot studies, and a good-faith final research project.

Academic Integrity Academic and scientific integrity compels one to properly attribute to others any work, ideas, or phrasing that one did not create oneself. To do otherwise is fraud.

We emphasize certain points here. In this class, talking to and helping others is strongly encouraged. You may also, with attribution, use the code from other sources. The easiest rule of thumb is, acknowledge the work and contributions and ideas and words and wordings of others. Do not copy or slightly reword portions of papers, Wikipedia articles, textbooks, other students' work, Stack Overflow answers, something you heard from a talk or a conversation or saw on the Internet, or anything else, really, without acknowledging your sources. See http://www.cs.cornell.edu/courses/cs6742/2011sp/handouts/ack-others.pdf and http://www.theuniversityfaculty.cornell.edu/AcadInteg/ for more information and useful examples.

This is not to say that you can receive course credit for work that is not your own — e.g., taking someone else's report and putting your name at the top, next to the other person(s)' names. However, violations of academic integrity (e.g., fraud) undergo the academic-integrity hearing process on top of any grade penalties imposed, whereas not following the rules of the assignment only risk grade penalties.

Resources

 

Lectures

Note that assignments will remain visible even when details are hidden.
#1 Aug 23: Course overview: scope, course goals, course design
  • Details will be appear here before each lecture.
Assignments/announcements:
  • Assignment A1 released
  • Student-information assignment released: see handout

Class images, links and handouts

Datasets

References

#2 Aug 25: Reviewing: a social experience?
Class images, links and handouts


Image source: Dorothy Gambrel, Cat and Girl. Permission policy here.

Lecture references

#3 Aug 30: Brown Bag and A1 Brainstorming
Class images, links and handouts

References on lecture topics

#4 Sep 1: Review helpfulness
Class images, links and handouts

Datasets

References on lecture topics

#5 Sep 6: From monologues to conversations

Class images, links and handouts

Datasets

References

#6 Sep 8: Conversation structure + A1 updates

References

#7 Sep 13: A1 presentations
Assignments/announcements
  • A1.R - A1 Reflection assignment
#8 Sep 15: (Breaking) conversation "rules"

Class images, links and handouts

References

#9 Sep 20: Intro to discourse-structure theory
Assignments/announcements

Class images, links and handouts

References

#10 Sep 22: Case study: from hypothesis to research
Class images, links and handouts

References

#11 Sep 27: Garley12Beefmoves-Mitra14Kickstarter

Class images, links and handouts

The readings

References

 

#12 Sep 29: Memes and relations

Assignments/announcements

Class images, links and handouts

The readings

#13 Oct 4: Nguyen10Bias-Vasilescu14R

Class images, links and handouts

The readings

#14 Oct 6: Paper discussions
Assignments/announcements

The readings

Oct 11: Fall Break
 
#15-16 Oct 16 and Oct 18: (Optional) Proposal consultation appointments
#17-18 Oct 18 and Oct 25: (Mandatory) Feasibility presentations to the instructors
#19 Oct 26:Advanced yet “off-the-shelf” features roundupp
Assignments/announcements

Class images, links and handouts

References

#20-21 Nov 1 and Oct 3: No lectures (EMNLP)
#22 Nov 8: N-Gram Language Models
Class images, links and handouts

Lecture references

#23 Nov 10: Entropy and Divergence
Assignments/announcements
  • Next week we'll have mandatory project progress-and-problems appointments. By 2pm the afternoon before your progress-and-problems appointment day, post a Piazza followup to your proposal that summarizes your progress and what discussion points or problems you'd like to bring up with me. Ideally, this followup post will be the agenda for your team's appointment, and will make the meeting efficient and useful for you.
Class images, links and handouts

Lecture references

#26-27 Nov 15 and Nov 17: Mandatory projects progress-and-problems appointments
#24-25 Nov 22: Entropy case study: language change. Review of practical research tips. Controlls in observational studies.
Nov 24: Thanksgiving Break
#27 Nov 29: Project presentations (mandatory attendance by all students for the whole session)

Assignments/announcements

Schedule on Piazza. Starting at 1:15pm
#28 Dec 1: Project presentations (mandatory attendance by all students for the whole session)

Assignments/announcements

Schedule on Piazza. Starting at 1:15pm

Final project description due: 12/09/16 4:30 PM (date determined by the registrar)

The main evaluation criteria will be the reasonableness (in approach and amount of effort), thoughtfulness, and creativity of what you tried, as documented in your writeup. Individual effort within team projects will be taken into account; see item 3 below.

  1. Use the ICWSM style files provided by AAAI (LaTex style and bib files, Word template)
    1. We make this requirement to facilitate submission to ICWSM 2017. However, note that your final-project submission should have your names and acknowledgments included, in a particular format (see item 1c amd 2b below); in contrast, you will want to strip any identifying information for ICWSM submissions.
    2. AAAI prefers non-numbered section headings. You may change the style files to include section numbers in your headings for the purposes of CS6742 submission.
    3. For the author heading, list only the names of your teammates that are enrolled in the class, even if you had external collaborators. (Reason: only students in the class are submitting the paper for a grade.) But see item 2b1 below.
  2. Include the following sections:
    1. "content" sections: abstract, introduction/motivation, data description (how you gathered, cleaned, and processed it), methods, an experiments, related work, references, conclusions (what you learned), directions for future work.
      • Make sure that your introduction section explicitly sets out your hypothesis or hypotheses.
      • Throughout, highlight your most interesting findings (positive or negative).
      • For the purposes of CS6742 submission, your related-work section does not need to be exhaustive; you may cover just a few most-related papers.
    2. An "acknowledgments" section: give the name and state the contribution of those who you received significant help from. (This may or may not include your advisor(s), your instructor, fellow students in the class).
      1. Authorship statement: if you intend to ask or have already arranged to have people other than your CS6742-enrolled teammates, also name each such person.
  3. Projects done collaboratively must also include a section describing who did what. External collaborators should be included in this enumeration.
  4. Use the number of pages you feel is appropriate.

Code for generating the calendar formatting adapted from the original versions created by Andrew Myers.