[  http://web.cs.dal.ca/~vlado/csci6509/project.html  ] Fall 2023 (Sep5-Dec6) Faculty of Computer Science Dalhousie University

CSCI 4152/6509 - Course Project

Page Content

• Choosing Project Topic
• Deliverables
  • P0 – Project Topic Proposal
  • P1 – Project Statement
  • P – Project Presentation
  • R – Project Report
• P1 and Project Report Style Notes
• Example Approach to Course Project
• Alternative Project Types
• Resources

Choosing Project Topic

The course project for graduate students (CSCI 6509), who are in a research stream (e.g., MCS, PhD) should follow the basic structure of a typical research project, such as the research work on a thesis, only on a smaller scale. The undergraduate students (CSCI 4152) can also choose a research project, or they can do a more implementation-focused project. The graduate students who are not in a research stream (e.g., MDI or MACS students) may select a research project, but they can also choose an application or business-oriented project with core methodology based on NLP.

You can form project teams of up to four students, or work individually.

The main deliverable is the final report, which should be in the form of a technical report and will be due at the end of the term. Student presentations will be scheduled towards the end of the term, and each presentation will be up to up to 8 minutes long, followed by 4 minutes reserved for questions and switching speakers. The research graduate students (thesis streams) are required to give individual presentations, while other students can choose to give individual or team presentations.

Regarding presentation dates, once the presentation time slots are shown on the course calendar, you will need to let the instructor know your preference by email. The presentations will be scheduled based on first-come-first-served basis.

Deliverables

• P0 – project topic proposal, by email, due on Friday, Sep 29, 2023,
• P1 – a project statement, using GitLab, due on Monday, Oct 30, 2023,
• P – oral presentation, book time slot early, submit slides or slides overview (PDF or PPT) using GitLab 24h ahead, and
• R – project report, submit using GitLab, due on Wednesday, Dec 6, 2023.

Note about emails: All emails related to the course must have the course number included in the subject, such as CSCI4152, CSCI6509, or, the best option, CSCI4152/6509.

In more details, your subject lines for two required emails must be:

• CSCI4152/6509: Presentation time
• CSCI4152/6509: P0 submission

P0 – Project Topic Proposal

Worth: 1% of the final mark
Due: Friday, Sep 29, 2023

You will need to choose a topic for your project. By the due date, you need to send to the instructor an email in plain text with the following information:

1. tentative title,
2. the list of team members, and
3. one paragraph description of the topic.

The following is a sample format of the email for P0:

To: Vlado Keselj <vlado@cs.dal.ca>
Subject: CSCI4152/6509: P0 submission

Hi,

This is our P0 submission:

Title: Classification Using Advanced NLP Technique
Team members:
 Firstname Lastname, CSID, Banner#, email
 First2 Last2, CSID2, Banner#2, email2
Description:
  This is a paragraph description of the research problem, including
  possibly some ideas about where to get data, and what methods to use.

Regards,
Firstname

P1 – Project Statement

Worth: 5% of the final mark
Due: Monday, Oct 30, 2023

Deliverable: The P1 submission is one PDF document that MUST be named p1.pdf (mandatory lowercase letters) and submitted using the project GitLab repository created by the instructor for the course by the P1 deadline.

By the P1 deadline, all project repositories should have been created in the FCS GitLab server and you should know your project id, which has the format P-dd, where dd is the number of your project; e.g., P-01, P-02, etc. The P1 submission must be submitted in the main directory of your GitLab repository. The exact location of the repository will be explained in an email sent to the class email list. If you want, you can also submit additional documents (such as the Word or LaTeX version, or the plain text version). The P1 document should be about 2 pages long, although it is perfectly acceptable to have a longer document. A document prepared in LaTeX is preferred since it is more likely to meet expected style and typesetting quality.

Content: The P1 document must include:

1. Project title,
2. Names of the member(s) of the group,
3. Problem statement,
4. List of possible approaches with citations to relevant work,
5. Project plan for the rest of the term, and
6. List of references.

Style: Style is a quite important component in evaluating P1 submissions. In addition to inciting student teams to keep working on the project during the term, a purpose of the P1 submission is to have a small exercise in preparing a small research paper in scientific style with appropriate use of fonts, sections numbers, citations, and references. You can find more notes on the style of P1 and the final report in the part P1 and Project Report Style Notes.

P1 will be marked based on its completeness, style and structure, clarity of presentation, and research on and analysis of related work. The P1 submission is a small test for submission of the final report. It is recommended that you use LaTeX. Present references at the end with full information in a way as typically done in research papers. Use appropriate citations in the main text to the list of references.

P – Project Presentation

R – Project Report

Worth 20% of the final mark.

The written project report is submitted in an electronic form using GitLab. The report must be a PDF file in the main project directory, and it must be named report.pdf. You can also submit additional code, data, and other files that you find relevant. The reports are kept in archive with the instructor for several years.

Peer evaluation is not currently a mandatory part of the evaluation scheme, but the students will be asked to submit their peer evaluation after project report submission. A peer evaluation consists of feedback about contribution of all team members to the project and it is useful to discourage and detect very imbalanced contributions and give stronger incentive to all members of a team to contribute. If peer evaluations indicate imbalance in contributions in a project team, they may affect individual marks for the report, in a positive or negative way.

A typical recommended structure of a project report for a reaseach-oriented project is:

• Title, Author(s), Course name,
• Abstract – make sure it is an abstract of the whole paper and not just a part of the introduction. The abstract should be brief, definitely not longer than a half of a page.
• Introduction – introduce the problem; get a reader's attention; explain motivation and significance of the problem, define project objectives. It is said that the title, abstract, introduction, and the whole paper should in a way express the same story in 10, 100, 1000, and 10,000 words, respectively. (Do not take these numbers literally!)
• Related Work – cover related work. Has this topic been studied yet? Do not just give an annotated list of citations. Give a critical analysis of the previous work.
• Problem Definition and Methodology – there is no good research without a research problem. Define it precisely. Describe your methodology, algorithms, system overview, or similar.
• Experiment Design – experiments are not mandatory, but some form of evaluation of your approach should exist. Evaluation, Discussion of evaluation results
• Conclusion
• References
• Appendices

P1 and Project Report Style Notes

P1 (Project Statement) can be considered to be a small exercise in writing the project report, and it should follow the same style guidelines, except the structure and the length.

The project report should be written in a good style from a technical Computer Science perspective. This is a bit loose specification. A couple of additional more concrete guidelines are provided below:

• use a readable serif font in the main body of the text, font size 10-12pt; e.g., Times Roman is a standard serif font, or TeX and LaTeX use a readable serif font by default;
• justified text in the main body (not ragged right, for example),
• Abstract and References parts should not be numbered, but the sections and subsections between them must be numbered and do not use colon (:) at the end of the section and subsection titles.
• Figures and Tables should be numbered and have captions at the bottom. (Tables may have captions on the top alternatively.)
• The document should be printer-friendly: use of color is okay, but no information should be lost after printing the document in black-and-white. There must be no large area of black or very dark color, since this is waste of ink and generally does not have a good appearance on a plain paper.
• The text should be readable and written in a narrative style in the sense that it should have a normal flow when reading. For example, it should not be mainly itemized. However, it should also not be purely narrative since it is a technical document, and it is expected that it contains some definitions, formulas, algorithms, code snippets, figures and similar (not necessarily all of those).

Example Approach to Course Project

1. Choose an NLP-related problem that is important and interesting in your opinion. You should have some ideas about how it could be solved, and about what interesting results you could obtain by the end of term. The discussed problem should be feasible in this sense, but it should not be trivial.
2. The next step is to search through existing published work and find out about existing solutions on the same problem, or to the closest similar problem. You can start with the textbook.
3. Design your method, implement it, and run experiments; possibly try method variations.
4. Analyze results. Revisit your methodology if needed.
5. Finish the report. Keep writing during the term.

While the above guidelines describe a typical research project in NLP, you can also consider some alternative forms:

Alternative Project Types

• theoretical project: You can focus on establishing a formal framework and proving theoretical results, usually regarding algorithm complexity of some solutions. Still, it may be a good idea to have some experimental results even in this type of project. This kind of project is still very research-oriented.
• implementation: You can put more emphasis on the implementational part of the project. This usually means developing a system prototype with multiple functionalities. In this case, you can devote more space in your report to the design, testing, and user documentation. This kind of project could fit well undergraduate students, and they could choose to implement some algorithm that is well-understood, and not necessarily very relevant to the latest research.
• software evaluation: Choose one or more existing software tools, download them, learn to use them, and use them to solve a problem. Report on your evaluation of the tool, instructions about its usage, advantages and limitations of the tool, and your particular approach. This kind of project is likely more appropriate for undergraduate students.
• survey: The survey format is a critical review of the current research in a narrow sub-area of NLP. If you choose this option, make sure that you do not cover a too wide, or already well-understood area, with published surveys on the topic. I would discourage you to go with this option, unless it is a part of your wider research program. It is difficult to write a good survey paper in a one-term time.

Resources

1. NLP Research Links on the course web page
2. http://acl.ldc.upenn.edu/ — ACL Anthology
3. Google scholar and other scientific Internet resources

Topics of Some Previous Course Projects