Tim McNamara

“Tourist’s guide to natural language processing”

I’ve put together a proposal to talk on natural language processing with Python. Would love your views on what should be included as content. If you’re in Wellington and would like to attend, feel free to turn up to the Wellington Python user group meeting on Thursday next this week.

I’ll have some time to build the talk together over the weekend. I want to know what’s interesting to others. If there are any interest in the plugins, please speak up. Likewise, if you have heard a buzzword in passing and want to know more about it - then send it through via Twitter or identi.ca.

Proposal

“Tourist’s guide to natural language processing” by Tim McNamara (@timClicks)

Synopsis

• A poor introduction to natural language processing
• A better introduction to NLTK
• Applying it to web applications

Possible plugins

If you’re interested in them, please let me know and I’ll include them in the talk.

• interactive discussion

  • how to store lots of text
  • privacy concerns of data mining

• getting text

  • scraping
  • copyright / intellectual property concernts

• Semantic Web

  • Linked Data
  • dbpedia.org
  • Freebase.com

• machine learning more broadly

  • overview of some tools (mainly Apache projects really)
  • optimisation (linear programming, genetic algorithms, simulated annealing, …)