- How to purify text?
- What does 'pure' mean?
- When is text pure enough?
- How to ensure the promises of (text) digitization are realized?
- What is the contributed value of using a lexical assessment database on top of ticclat?
- Calculate performance of ticcl without using the lexical assessment database
- On what corpus?
- Create benchmark corpora for the lexical assessment database
- With different distributions of relevant and irrelevant data
- Calculate performance of ticcl with lexical assessment database (containing different datasets)
- Calculate performance of ticcl without using the lexical assessment database