xiao11lam/PuzzLing-and-Scoring

PuzzLing combines the full system for the CALL(Computer Assisted Language Learning) platform especially focusing on low-resource languages, which includes language scoring and feedback functions. # PuzzLing and Scoring System ## Mockup Preview ### Folder Structure ```sh . ├── .idea ├── Data # the dir for storing the testing and validation corpus │   ├── arabic_text.txt # the Arabic sentences in formats │   ├── english_text.txt # the English sentences in formats and in parallel with the arabic │   ├── WikiQAArticlesCorpusAr-En.tsv # the short phrases │   ├── WikiQAQuestionsCorpusAr-En.tsv # the long sentences ├── static # include all the styling files for the front-end │   ├── img │   │   ├── fonts │   │   └── styles │   ├── styles │   │   ├── style.css ├── templates # the web structure of the frontend │   │   ├── index.html │   │   ├── score.html ├── README.md ├── app.py # the python Flask web deploying file ├── get_data.py # the corpus cleanning scripts ├── logic.svg ├── logic_graphviz.gv . ``` ### Main Window ### Scoring Feedback Window ## What is PuzzLing? **PuzzLing** combines the full system for the CALL(Computer Assisted Language Learning) platform especially focusing on low-resource languages, which includes language scoring and feedback functions. With the support from the latest language processing toolkit of the Neural Space, we aim to give a general evaluation and retrieve the error places that the testers can improve. Our related using area can be automatic language scoring, evaluation, derivation— L2 teaching, Education of English as Foreign Language, etc. ## What is new about PuzzLing compared with other platform? For our target testers, their mother tongue (L1s) varies from many kinds of low resource languages such as Pashto, Arabic and Hindi, etc. And we intend to expand the scale of our current testing languages continuously in the future. To the best of our knowledge, our platform can be the first proposed non-native English scoring system for people who are speaking low-resource languages. ## Motivation As we know, although the English language scoring system has made a pr …