Machine Translation Course & Roles

• Roles
  • Author
  • Data Scientist
  • Scientific reviewer
  • Engineer
  • Visionary
  • Attendees
• Lab Projects
  • Project ideas
  • Project template

Course Roles

Each person is assigned a role (almost randomly) and must prepare the reading from the Materials column from the row where their name is added. Materials will be announced shortly. Consider taking these roles seriously as they account for half of your grade. Since December, 2 is during a public holiday, we can postpone the presentations for Thursday, December, 8.

Author (A)

Pretend you are the main author of the papers, prepare a presentation and talk about:

• Problem definition: present what problems the authors intend to solve and present the context and necessity of why it is important to adress the problems.
• Methodology: present the methodology, the mathematical foundations; find an explanation for why this methodology is suitable for the problems at hand.
• Experimental findings: present the main results, how they compare with previous work.
• Get into as many details as possible; the appendices in the paper should also be covered.

Data Scientist (DS)

Find the dataset used in the paper, prepare a dataset description. Take the entire dataset or a subsample (if it’s too large) and prepare a notebook, some tabels and a series of plotly plots with an Exploratory Data Analysis (statistics, number of words, type-token ratio, number of sentences, means and standard deviations, distribution plots, tokenizer fertility, perplexity etc.). This is role requires code, plots, analyses.

Scientific reviewer (R)

You must make a critical evaluation of the paper, not necessarily negative; read the guidelines and examples from NIPS

• Summary and contributions: Briefly summarize the paper and its contributions
• Strengths: Describe the strengths of the work. Typical criteria include: soundness of the claims (theoretical grounding, empirical evaluation), significance and novelty of the contribution, and relevance to the Machine Translatiion community.
• Weaknesses: Explain the limitations of this work along the same axes as above.
• Correctness: Are the claims and method correct? Is the empirical methodology correct?
• Clarity: Is the paper well written?
• Additional feedback, comments, suggestions for improvement and questions for the authors
• Overall score

Engineer (E)

Implement something related to the paper either on the same dataset or on a new one; prepare to share the code and some empirical intuition behind the paper.

• Reproducibility: If the original authors already provide the code, try to run it on a new dataset.
• Comments: Are there enough details to reproduce the major results of this work?
• Efficiency: Measure the time it takes to run the code, provide an assement of how suitable the approach is for being run at scale.

Visionary (V)

Propose a follow-up research project or a new application; take into account the previous work and existing work being done; take into account ethics and the socio-economic impact:

• Relation to prior work: Is it clearly discussed how this work differs from previous contributions?
• Have the authors adequately addressed the broader impact of their work, including potential negative ethical and societal implications of their work?
• Does the submission raise potential ethical concerns? This includes methods, applications, or data that create or reinforce unfair bias or that have a primary purpose of harm or injury. If so, please explain briefly.

Attendees

Everyone must ask a question at the end of the presentations to qualify as being present. Being present at all the presentations will account for 1 bonus point at the end.

Lab Projects

1. gather some colleagues and make a team of maximum 3 people
2. choose an MT topic that you would like to research (see the project list on the website or propose your own)
3. make sure your topic does not overlap with other topics that are in progress and that have been chosen by your colleagues
4. email sergiu to announce your team, your proposal and to discuss how to approach it
5. after you obtain the approval, mark it as being in progress on the kanban list and start working on it
6. prepare the project, a presentation, and a report using this template
7. place everything in a digital storage space somewhere: a git repo, a drive, some file on a server etc.; don’t send large files by email, send only URLs
8. current deadlines are December 23, January 13, and January 20