Skip to main content

Independent Study Coursework Plan

Early posts to this website will relate to an Independent Study course I'm completing this semester.  This post is the bulk of my Independent Study coursework plan. It's subject to change at regular intervals, with instructor permission.

Title of Course

Extracting Symbolic World-States for Open-World Interactive Storytelling

Credit Hours

3

Overview

Individual investigation of advanced topics under the discretion and direction of the instructor.

Course Website

JenniferMarieNelson.com

Independent Study Goal/Statement of Purpose

I’m using this independent study as an introduction to conducting impactful self-directed research. I want to tackle graduate-level problems while the stakes are still low as an undergraduate. I hope to learn to read like a researcher, model interesting and hard problems, and put that model into practice.

Course Objectives

    1. Describe, discuss, and explain the research problem studied, the approach taken, the experimental design, the analysis of data, and any conclusions drawn from the Independent Study.
    2. Explain and apply the basics of planning, narrative theory, and methods for symbol extraction from texts.
      a. Find, understand, summarize, apply, and analyze relevant literature.
      b. Summarize a batch of foundational literature.
      c. Conduct wide review comparing methods for symbol extraction.
      d. Regularly summarize future batches of literature.
    3. Develop publishable progress on the problem.
      a. Design a model and incorporate feedback.
      b. Code a system implementing the model.
      c. Test incrementally as system is built with defined, reasonable benchmarks.
      d. Write a formal test to be executed next semester.
    4. Assemble research on the problem in an accessible way.
      a. Keep project and research open-source.
      b. Keep instructor regularly updated on the project’s progress.
      c. Write three formal progress reports.
     
      d. Draft and revise elements of a publishable paper.


    Research Plan

    Deliverables:

    - Four Literature Batch Summaries. (1 summary / 4 papers approximately)
        - 1st Batch: Foundational literature batch
         - 2nd Batch: Symbol extraction methods review
        - 3rd and 4th Batch TBD, as project progresses.
    - Statement of Research Problem (with hypotheses to test)
         - Three formal progress reports describing the:
               - State of project
               - Steps accomplished
               - Challenges faced
               - Plan for challenges
               - Proposed updates to this plan, for discussion with instructor
    - Model, with write-up and possible presentation
    - System implementing the model (with write-up)
         - Three or more benchmarks for the system to reach
    - Formal test/benchmark formulated, planned for next semester

    Timetable
    Week
    Due Date (Fridays)
    Activity
    Relevant Objective
    (Every week)

    Regular informal updates
    4.b
    1
    8/31
    Semester Plan Draft
    4.b
    2 -Labor Day
    9/7
    Semester Plan Finalized
    4.b
    3
    9/14
    Literature Batch Summary 1
    (Foundational Literature Summary)
    2.b
    4
    9/21
    Literature Batch Summary 2
    (Symbol Extraction Summary)
    2.c
    5
    9/28

    Progress Report 1
    4.c
    Statement of Research Problem
    1
    6
    10/5
    Model draft / feedback
    3.a
    8
    10/19
    Model revision
    3.a / 4.d
    9
    10/26
    System design / feedback
    3.b
    10
    11/2
    Progress Report 2
    4.c
    Proposed system benchmarks
    3.c
    UROP Funding Application Due
    1
    11
    11/9
    System Functionality Test
    3.b
    Literature Batch Summary 3
    (TBD Literature Summary)
    2
    12
    11/16
    Benchmark 1
    3.c
    13 - Thanksgiving
    11/22
    Formal test draft
    3.d
    14
    11/30
    Benchmark 2
    3.c
    Formal test revision
    3.d / 4.d
    15
    12/7
    Benchmark 3
    3.c
    Final Progress Report
    4.c


    Note that the dates in this timetable are subject to adjustment, with instructor approval. The student is encouraged to re-evaluate this timetable with each Progress Report, and suggest alterations.

    Grading

    Scale

    Grade Range [Inclusive, Exclusive)
    Letter Grade
    Points
    Explanation
    93 or greater
    A
    4.0
    Excellent performance, superior achievement
    [90, 93)
    A-
    3.7
    [87, 90)
    B+
    3.3


    Good performance, substantial achievement
    [83, 87)
    B
    3.0
    [80, 83)
    B-
    2.7
    [77, 80)
    C+
    2.3


    Standard performance and achievement
    [73, 77)
    C
    2.0
    [70, 73)
    C-
    1.7
    [67, 70)
    D+
    1.3


    Substandard performance, marginal achievement
    [63, 67)
    D
    1.0
    [60, 63)
    D-
    0.7
    [0, 60)
    F
    0.0
    Unsatisfactory performance and achievement

    Breakdown

    25%  - Model Write-up (after revisions)
    15%  - System Benchmarks
    10%  - System write-up
    20%  - Progress Reports
    10%  - Plan for Formal Test (after revisions)
    10%  - Literature Batch Summaries
    5% - Presentation of Work
    (Ability to speak clearly about work in both formal and informal settings.)
    5% - Participation in Lab

    Comments

    Popular posts from this blog

    Research Question

    Research Goal(s) Sep 28th, 2018

    Below is an outline of the research direction this project will pursue. This is a big set of problems, and can't be solved in one independent-study. I'd like to get as far as possible with this problem over my remaining undergraduate years, spinning an Honor's Thesis out of it.
    Goals: Build a natural language to symbolic language interpreter with the following capabilities:
    Given a domain, current state, and a natural language player request, can translate that request into symbolic actions, objects, and predicates.
    The translated symbols should make sense, be reasonable, and have some support for influencing (i.e. search within a genre)
    The translated symbols can then be incorporated into the domain and state, for a narrative planner to work with as appropriate. (Incorporation may even involve modifying existing symbols, or previous states in a plan.)
    I.e. if the domain is blocks world and user input is "drop block A off the table,"…

    Foundational Literature Review 1

    For this review I read 2 papers and a textbook chapter. This will be followed up by a more detailed review of the paper on learning STRIPS actions.

    Apologies for not embedding this literature review directly into the post. I wrote it in markdown, hoping that would translate easier to the web, but I also used lots of LaTeX and a few diagrams in Mermaid. For now, I have a pdf.

    Foundational Literature Review