Due: January 20, 2022 (for students who registered late, the assignment is due one week after registration).
The written assignment should describe an original, future application that requires the processing of human language. The application can be on any aspect of natural language processing, for any human language. You will express the motivation for such an application, outline its design, and discuss its implications.
The written assignment must be a new effort, conducted specifically for this class. You may build on and extend previous research, but this assignment needs to add to that research, not just reuse old material.
The written assignment is an individual assignment. You may not work in teams, or collaborate with other students or authors. You must be the sole author of 100% of the work you turn in.
The assignment should be written in English using your best academic style, on one letter-sized page with 11-point font, 1-inch margins, single column format (approximately 500 words). The content should address the following points:
Motivation: Why is this application useful? What problem does it solve? Why does the solution require the processing of human language?
Design: How does the application work? What are its inputs and outputs? What processes does it use internally?
Analysis: What are the limitations of the proposed application? Are there any alternative solutions that could work better, or differently? What would be the implications if such an application were put into use?
Other considerations
Do not put your name or student ID on the essay (the assignment is graded directly in Blackboard).
A concise, short title for the essay is useful, but is not required.
Section headings may be used if you wish, but are not necessary as long as the main points above are addressed.
I recommend against including graphics. While graphics may help clarify an idea, they are not a substitute for a textual description, and they do take up space.
References should be cited if you borrow specific ideas from published sources. However, the assignment should focus on your own original idea. If you do not use specific ideas from existing papers, you do not need to cite any references.
Submit the assignment as a PDF file using the “Application Idea” assignment on Blackboard. Make sure that it is in PDF format and exactly one page (with other formats like Word, Blackboard sometimes messes up the pagination).
The grade for the assignment will be broken down as follows, using the rubric in Blackboard.
20% Motivation: a clearly articulated problem with real-world implications.
20% Design: appropriate considerations for the inputs, outputs, and processes for the application.
20% Analysis: Critical evaluation of the proposal, alternative solutions, and potential implications.
20% Creativity and thoroughness.
20% Quality and clarity of writing.
The application idea counts for 5% of the overall course grade.
Does the application need to be on one of the research areas from the course schedule? The application can address any problem that involves the use of real-world human language data; it does not need to fall under the research areas that will be discussed in class.
Does the application need to use one of the methods from the course schedule? The constraint is on the problem (human language processing), not the methods. Any suitable model is fine, whether it will be discussed in class or not.
How can we design a solution when we're not yet familiar with basic NLP algorithms? The precise algorithms don’t matter for this assignment. What is important is identifying a real-world problem, and sketching a way to address it.
Is it OK to propose the use of NLP methods for an application in domains other than human language? The application must involve the processing of human language.
Is it OK to propose an application for human language together with some other domain? It is fine to model human language together with another domain, as long as the focus is on the language part. For example, an application idea that creates text descriptions of financial data, or predicts financial trends from human language texts, can be appropriate for this assignment if it concentrates on the language aspects; but if most of the work is on modeling the financial data, this can be a very interesting application, but it is not appropriate for this assignment.
How do I express the motivation for an application? The starting point should be the problem that the application is trying to address: What is it trying to do? Why would this be a useful thing? The motivation should guide the development of the rest of the paper. How can we tell if an application is good for its purpose? What inputs, outputs and processes can be used to achieve this? What are the advantages and disadvantages of the proposed design for this particular purpose?
Can the application propose an improvement to an existing NLP process? Proposing an improvement to an existing process would be extremely difficult at this stage (and if you already know so much about NLP that you can make a compelling case for such an improvement in one page, then you're probably too advanced for this class). Instead, try to think of an original application.
Should the essay consider moral and ethical issues? For certain applications, there may be practical and ethical considerations about using an automated model for the proposed application in the real world; such considerations should be highlighted in the analysis.