LAC: Language and the Computer

Project 1: Vocabulary Game

This project constitutes 30% of your final grade for LAC. Please work on the final program and report individually.

The goal of this project is to learn how to extract data. You will write a program to extract data for six languages:

• Chinese
• Czech
• Indonesian
• Japanese
• Korean
• Vietnamese

Then you will use this in a simple vocabulary testing game.

Finally you will describe what you have done, including a description of what you could and could not extract, and comments on the data. Write a short future work section describing what you would like to do if you had more coding knowledge (or different data).

You can use the code from week 6 to get started.

Minimal Requirements

1. Extract data from all six languages
2. Summarize the data for each language (at least: number of Skills, number of Lessons, number of Words)
3. The game should first list the available languages and ask you to choose one, then give a word and ask for its translation (or q for quit).

Stretch Goals

Do at least one of the following:

1. Improve the extraction process, e.g.
   • Save the metadata separately and analyze it
2. Improve the game
   • Ask which skill they would like to do, or which level?
   • Ask questions in a random order
     use the random module, i.e. random.choice()
   • Randomly ask questions from earlier modules
   • Spice up the feedback
     • Have a random choice of feedback
     • Have feedback in the different languages
3. Allow people to go in either direction English-X or X to English

Write up

• The paper should be up to six pages, include a title, date and name on the first page, you do not need a separate title page.
• The paper should be single spaced.
• In the write up you should describe what you found out about the difficulties of extracting data
• You should give concrete examples from the resource you analyzed.
• Include quantitive results.
• Include representative examples.
• Link to your program in coogle colab or if you wrote it locally, zip it up and email it to me. This does not count toward the six page total
  In the main paper describe generally what the program does (no need to go into extreme detail)
• If you want to make it even more beautiful, as I am sure you do, take a look at my (Computational) Linguistic Style Guidelines: a guide for the flummoxed.
• Submit softcopy (via moodle).
• The deadline is on the main page..

References

• Duolingo Fan Wiki

LAC: Language and the Computer Francis Bond.