CS297 Proposal
AI Quantification of Language Puzzle to Language Learning Generalization.
Harita Shroff (harita.shroff@gmail.com)
Advisor: Dr. Chris Pollett
Description:
Online language learning applications have gamified the objective by providing multiple ways/games to learn a new language. Some of the ways include rearranging words in the foreign language sentence, filling in the blanks, providing flashcards and many more. Primarily this research focuses on quantifying the effectiveness of these games in learning a new language. Secondarily my goal for this project is to measure the impact of some exercises on completing other activities on these language learning platforms.
Schedule:
Week 1:
Aug 26 - Sept 1 | Kickoff meeting with Dr. Pollett. |
Week 2:
Sept 2 - Sept 8 | Join Duolingo and study a language to gather data. Study Chapter 1 of Introduction to Deep Learning. |
Week 3:
Sept 9 - Sept 15 | Prepare slides for the chapter 1 of Introduction to Deep Learning. |
Week 4:
Sept 16 - Sept 22 | Keep working on the chapter 1 slides and prepare list of Duolingo game activities. |
Week 5:
Sept 23 - Sept 29 | Deliverable 1: Provide Feed-Forward Neural Network working program for Gujarati language digit recognition. |
Week 6:
Sept 30 - Oct 6 | Study Chapter 2 of Introduction to Deep Learning |
Week 7:
Oct 7 - Oct 13 | Prepare slides for the chapter 2 of Introduction to Deep Learning |
Week 8:
Oct 14 - Oct 20 | Study Chapter 3 of Introduction to Deep Learning. |
Week 9:
Oct 21 - Oct 27 | Provide slides for chapter 3 of Introduction to Deep Learning. |
Week 10:
Oct 28 - Nov 3 | Study Chapter 4 of Introduction to Deep Learning. Keep working on Deliverable 3. |
Week 11:
Nov 4 - Nov 10 | Provide slides for chapter 4 of Introduction to Deep Learning. Keep working on Deliverable 3. |
Week 12:
Nov 11 - Nov 17 | Keep working on Deliverable 3 and start looking for dataset for Deliverable 4. |
Week 13:
Nov 18 - Nov 24 | Complete Deliverable 3 and Deliverable 4 |
Week 14:
Nov 25 - Dec 1 | Start a draft for CS 297 final project report |
Week 15:
Dec 2 - Dec 8 | Validate all pages on the website and keep working on Deliverable 5 |
Week 16:
Dec 9 - Dec 15 | Deliverable 5: Complete CS 297 final report |
Deliverables:
The full project will be done when CS298 is completed. The following will
be done by the end of CS297:
1. Provide Feed-Forward Neural Network program using tensorflow to identify Gujarati language digits.
2. Provide Convolutional Neural Networks program using tensorflow to identify Gujarati language digits.
3. Implement the word2vec program to find word embedding for Gujarati words.
4. Data collection.
5. CS297 final report.
References:
[E. Charniak 2019] “Introduction to Deep Learning”. Eugene Charniak. The MIT Press. 2019.
[J. Grego 2012] “Duolingo Effectiveness Study”. John Grego, Roumen Vesselinov. 2012.
[D. Huynh 2018] “An Assessment of Game Elements in Language-Learning Platform Duolingo”. Duy Huynh, Long Zuo, Hiroyuki Iida. 2018. |