JSP3

Semester project 3 for Linguistics

• analyze some text
• learn techniques for analyzing text
• learn some software engineering skills
• learn git, markdown, use LaTeX

• who chooses the task? you or me?

• how many tasks? 1, 2 or 4

• how many teams? 1, 2 or 4

• Introduce yourselves

  • name
  • languages spoken (natural/programming)
  • interests (relevant to the course)
  • one fun fact (not relevant to the course)

• your choice!
• LLM text vs Human text
  • what is different (test for Czech?)
  • I have data for English
• Distribution of lexicalized metaphor
  • combine sense-tagged text with ChainNet
  • analyze distribution
  • fill in what is missing
• Improve Czech wordnet
  • fill in Czech specific patterns
    • adverbs [of languages]
    • diminutives
    • aspect variants
    • gender variants (role nouns)
  • generate definitions
  • get examples from corpora
  • derivational links with affixes?

• get something useful for each task
• combine to make a best-of-breed
• write, submit and publish a paper
• release at least one automatically tagged, aligned corpus

• use github to coordinate
  • GitHub quickstart
  • git an Introduction

• 15-30 minutes progress

• longer discussion of issues as necessary

• small meetings pair+me or WSD+me, .... as necessary

• ALL make github account
  • send me accountname
  • I will add to github