Slides from my recent talk at the SLTC workshop on unsupervised methods in NLP

I gave a talk at the recent SLTC workshop on unsupervised methods in NLP. Here are the slides. My main points were

  1. to stress that the task of language technology research efforts should be to build knowledge representations of some sort, preferably as explicit as possible;
  2. even in an unsupervised research effort, hypotheses must be stated;
  3. for research purposes the explanatory level of the resulting knowledge representation must be non-trivial;
  4. for engineering purposes, the knowledge representation must be designed answer to stated requirements.
  5. Quite often, these various goals are conflated. My talk was a bit grumpy, but I still really like unsupervised methods.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s