Skip to main content

Resources & Requirements


Paper Presentations

  1. Each one of you should choose two papers, from two different categories. The order of the paper presentations will roughly be the chronological order of the papers, but we may deviate from it from time to time, to accommodate constraints and/or to have a sensible order of presentations.In addition, please choose 2 papers to be a discussant of.

  2. Each Presentation will be 20 minutes, followed by 10 minutes discussion.

  3. Following each paper presentation, the presentation will write a short (half a page) summary of the paper and the discussion.

  4. In the week before your presentation, please come to Dan's Wednesday office hour to discuss your presentation.

  5. Template for Paper Presentations Download the powerpoint template - Follow this template as closely as possible

Choose papers to present/discuss here: Paper Presentation Selection Sheet

We will put the dates for presentations within a couple of days.


Critical Surveys

  1. You will write 4 critical surveys. Please submit these surveys on of before February 11, March 1, March 24, April 15.

  2. Two of these can be (but do not have to be) on papers you served as a discussant for.

  3. A critical review will be up to one page, 11font; please do not spend more than a third of this page to describe what the paper is doing. Use the rest of the space to provide a critic of the paper (what's good, what's bad; what you think is interesting; what they should have done better; your suggestions for improvements and/or for additional work in this direction, etc.

  4. Please send your review as an email message to Dan and Nitish, with the subject line CIS700dr Review #[1,2,3,4] studentid

Here is a great critical survey written by a student that can be used as a reference for how to go about writing paper critics.


Project 1: Reproducing a Paper's Results

This project requires you to reproduce the results of a paper. This project needs to be done individually; put your name below the paper you would like to reproduce in the following spreadsheet – Project 1 Paper Selection Spreadsheet

The data required for all the papers is available online.

One of the following paper can be chosen:

  1. Extracting Commonsense Properties from Embeddings with Limited Human Guidance
  2. Global Learning of Typed Entailment Rules
  3. Modeling Semantic Expectation: Using Script Knowledge for Referent Prediction
  4. How Much is 131 Million Dollars? Putting Numbers in Perspective with Compositional Descriptions

For the fourth paper 'How Much is 131 …', it is highly recommended that you use AllenNLP. It will make writing code really easy, and is a great tool to learn for writing NLP research code in general. Using Pytorch, Tensorflow or DyNet is fine as well.

The submission deadline for this project is 11th March. Further details on what is expected to be submitted will be posted at a later date.


Pytorch Tutorials

These tutorials do a good job of introducing Pytorch.


AllenNLP

AllenNLP is a Open-source NLP research library, built on PyTorch. It is widely used in the community now and it will be useful to make yourself familiar with it.