Last Modified: March 5, 2017
CS 295: Statistical NLP: Winter 2017
Project Status Report
Sameer Singh
http://sameersingh.org/courses/statnlp/wi17/
As the third submission for your course project, you will be submitting a project status report. Each project
report (one per group) will be a maximum 5 page PDF write-up uploaded to Canvas by March 7, 2017.
What to Submit?
The project status report is intended to be a draft version of your final report, with much of the problem setup,
proposed approach, evaluation criteria, and study of related literature complete, and a description of the progress
so far, and expected concerns. The report should be structured slightly differently from the proposal, to make it
much more like a research paper submission. Here are the sections I anticipate you to have in your report.
◦ Title of the Project: Come up with a succinct title that describes what is novel about your project.
◦ Abstract: A paragraph-long summary of your project, should be a shorter version of the introduction.
◦ Introduction: A complete summary of your project, with the following structure (1 paragraph each):
◦
Setup the main motivation for the general area. This is not asking for the motivation behind your
particular approach, but instead why is the task important in the first place. For example, if you are
doing something in Visual QA or caption generation or text summarization, describe why these are
important problems and where do they get applied.
◦
Provide a brief summary of what people have done so far, and what are their shortcomings. This is the
actual motivation for your work, these are the shortcomings you are addressing in this work.
◦
Describe in brief what the main idea behind your work is, and how you think it will address the
shortcomings described in the previous section.
◦
Summarize the evaluation setup and results so far, with a sentence on what you expect to attain by the
final report.
This is not a strict template, but unless you have a regularly publishing senior PhD student in your team, it
would be best for you to stick to this structure.
◦ Related Work:
A few paragraphs on related work. Identify at least 4
−
5 papers that are most relevant to
your project, and describe each of them in a single sentence or two. If not redundant with the introduction,
include a paragraph on how your contribution is different from the ideas and results produced in other
papers. This is the main section that where you will argue the novelty of your project.
◦ Approach:
Technical summary of your proposed approach. Use notations, equations, and figures to assist
your description, i.e. just saying “softmax on an LSTM” is not good enough.
◦ Experiments:
Describe the evaluation setup, baselines, and metrics, and include the results of the evaluation
so far, using tables, graphs, plots, etc. as needed.
◦ Conclusions and Anticipated Problems:
Summarize your existing results, ones you expect to obtain by
the final report, and a list of issues/concerns that might prevent you from obtaining them.
Depending on your project, it may not make sense for you to stick to these descriptions too closely, so please
feel free to deviate from this structure if needed.
L
A
T
E
X template
Optionally, I encourage you to use the ACL 2017 L
A
T
E
X style files for this report. The style files are available
here:
http://acl2017.org/downloads/acl17-latex.zip
. Please use
aclfinalcopy
option, as described in
the example. Note, using these style files will be a requirement for the final report.
Project Status Report UC Irvine 1/ 1
