- Course number
- CIS 700 - Reasoning for Natural Language Understanding
- Instructor
- Dan Roth
- Website
- seas.upenn.edu/~cis700dr/Spring20
- Discussion Forum
- Piazza
- Time and place
- Spring 2020, Mondays and Wednesdays 1:30-3pm (LRSM 112B)
- Course Description
- Humans engage in reasoning – we make decisions that involve assigning values to multiple interrelated variables, involve multiple interdependent steps, and involve the use pf discrete computations (logical or others) over inferred variables. Moreover, these computations often requite incorporating common sense and background knowledge about the world around us. Altogether, these capabilities seems to be at the heart of facilitating robust behavior in new situations.
The success of statistical and deep learning methods has supported significant advances in some aspects of AI, especially those that depend on learning standalone models from large amounts of annotated data. But our models still do not know to respond to surprising questions such as “Did Aristotle have a laptop?”, understand what is meant when the response to “what would you have for dinner” is “I am not sure; I had a big lunch”, or reliably solve algebra word problems that require both text understanding and some “reasoning” capabilities.
The goal of this class is to understand the literature – old and new – on theories of reasoning – especially in the context of natural language understanding.
You will read, present and discuss papers, and work on two projects. A small, well-defined one, in the first third of the semester, and a large and open ended one in the rest of the semester.
- Prerequisites
- Machine Learning class; CIS 419/519/520 or equivalent. NLP: Knowledge of NLP (equivalent to a basic Computational Linguistics/NLP class).
- Grading and Expectations (subject to further adjustments)
- There will be
- Course Projects (50%) - The first project will be an individual project, and will focus on reproducing a relevant result from the literature (more details will be given later). The second project will be done in teams of size 2; teams will propose projects and consult us. The first project will occupy the first third of the semester or so and will be presented once it is done. The second will begin then with a brief project proposal, and will consume your time until the end of the semester. We will have a couple of milestones along the way, and results will be reported and presented at the end of each stage.
-
Reading assignments - Mandatory readings and additional recommended readings will be assigned every week.
-
Critical Surveys (20%) - Four (4) times a semester you will write a short critical essay on one of the additional readings. In two of these you will be assigned as a discassant of a paper presentend by another student.
-
Presentations (20%) - You will present two papers from the additional readings (30 minutes, focusing on the mathematical/technical details of the paper). In some cases, the presentations will be prepared in groups, and a group of presentations will form a coherent tutorial. In all cases, following your presentation you will write a short summary of the paper and the discussion that followed (a template will be provided).
-
Class Participation ( 10% )
There is no final exam.
- Expectations
- This is an advanced course. I view my role as guiding you through the material and helping you in your first steps as a researcher. I expect that your participation in class, reading assignments, and presentations will reflect independence, mathematical rigor and critical thinking.