Y Tiwtiadur (https://ytiwtiadur.corcencc.org/) is a website that collects tools designed for data-driven teaching and learning of Welsh. In the context of the CorCenCC project (https://corcencc.org), four tools were developed:
- Gap-Fill (Cloze) tool allowing teachers to delete words from a text at specified intervals to encourage or assess comprehension abilities and prediction strategies - Vocab Profiler tool that enables the grading of texts by word frequency - Word Identification tool testing learners' ability to guess a word in context - Word Task Creator tool that facilitates intensive work on a specified vocabulary item.
The goal of this project is to improve one (or more) of the existing tools, or implement new ones levaraing the CorCenCC corpus or other resources. For example, the Word Profiler currently analyses the quality a text solely based on the frequency of the words used. However, other syntactic and discourse features could be incorporated. Same with the other tools. Interested students are encouraged to test the tools beforehand.
Ideas from the student(s) taking on this project are more than welcome, so that it can be tailored to specific interests and abilities.
It is likely that some natural language processing (NLP) tools would be used in the project, but previous knowledge of NLP is not required. At the same time, knowledge of Welsh would be desirable (as native or learner levels).
Please, do not hesitate to reach out if you have any questions.