search

syllog1sm / redshift

Transition-based statistical parser
419 stars 52 forks source link

Documentation for redshift #8

Open ghost opened 10 years ago

ghost commented 10 years ago

Hello! I am using redshift for the first time, and I am unable to find any documentation regarding the functionalities of the libraries. Can you please tell me where I can start with redshift?

Also, can you tell me what /tmp/stanford_beam8 is?

ebeckm commented 9 years ago

Hi Angefonce. You have to train the parser before you can use it. The process for doing so is explained in the README.

The author probably stored the output of train.py in /tmp/stanford_beam8 before running his code. My guess regarding the naming convention is as follows: beam8 refers to the beam width used when training the model; Stanford refers to the training data, which may have been obtained by applying the Stanford Parser to a plain text corpus of some sort.

Edit: this blog post describes how the model is trained.