Reaction Comments
To help presenters direct class discussions better, everyone is
expected to write a set of short reactions for each assigned paper (in
the form of NB annotations). Your reactions should not summarize
the paper. Instead, they should focus on your critique of the
paper. You might find
links to
resources for paper reading and paper reviewing helpful (from a course I taught at Pitt).
Mandatory requirements:
- Always include one annotation that explains whether and how
you think the paper is interesting from an NLP perspective. What are
the opportunities and challenges in applying NLP to this problem? If
not published in an NLP venue, how would this work need to be changed
to contribute to the NLP community?
-
Also contribute (at least) one additional substantive
annotation per paper. Your annotations may have a
number of forms: (a) You may compare the work to related material; (b)
You may hypothesize about ways in which the work could have been
improved; (c) You may think about ways to expand on the work
(conceptually or computationally); (d) You may critique the work,
including its conceptual framework, methodology, and/or results.
Other options:
Additional substantive annotations and/or responses to other posts, as well as
descriptions of things you don't understand that you would
like the class to discuss, are encouraged.
Grading:
Reaction annotations are due by
16:00 two days before the class during which the paper
will be presented (that is, 48 hours in
advance). This will give the presenter time to tailor the
presentation to the interests and needs of the class.
For cach class, you will receive a commentary score of 1 (satisfactory) or 0 (unsatisfactory).
Late assignments receive 0.