Scala NLP | Hacker News Reader

Scala NLP

scalanlp.org

53 pointsjondot8 comments

Huh, I was wondering why I had a bunch of stars on github in the last few hours. (Sad there's no analytics for Github projects.)

I'm the lead author of ScalaNLP, and I'm happy to answer questions. It's mostly a scaffolding library for other systems. There's not much that works "out of the box."

I am currently working on releasing Epic (hopefully tomorrow), which is my parser/structured prediction framework, that will be a little more useful to non-specialists.

I spent some time earlier this year exploring various NLP engines (Freeling, OpenNLP, DELPH-IN, LingPipe, UIMA, and a few others). Of them, FreeLing (http://nlp.lsi.upc.edu/freeling/) was far and away the technical leader for my needs:

  - Decent documentation
  - Relatively easy to compile and install
  - Working (and practical) example code
  - Easily configured
  - Extremely flexible design
  - Supports many written languages
  - Supports Java, C++, and has a simple client-server model
  - Good execution time (fast code)
  - Solid code base (no crashes in six months)

Do you know of any that have a semantic role labeling feature? I've been looking for one for a while with no luck.

SENNA by Collobert + Weston do SRL. It's free for non-commercial use.

Hoifung Poon's unsupervised semantic parser can be used for SRL. It's available as open-source (I think?), but will require more work out of the box to get it working. Namely, you'll have to train it on your data, and convert semantic parses to SRL.

Thanks. I also found this, which I think I'll try: http://www.surdeanu.name/mihai/swirl/

Those interested in this may also find Factorie interesting: http://code.google.com/p/factorie/

Factorie's a nice piece of work, I highly recommend it. The team at UMass has done a great job.

Can I plug our API? I'll plug our API: https://www.repustate.com/docs

As another commenter mentioned, freeling is great.

Reply on news.ycombinator.com