eng-dependency-stanza

This analysis is used with Sparv. Check out Sparv's quick start guide to get started!

To use this analysis, add the following lines under export.annotations in the Sparv corpus configuration file:

- <token>:stanza.ref  # Token IDs relative to their sentences
- <token>:stanza.dephead_ref  # Sentence-relative positions of the dependency heads
- <token>:stanza.deprel  # Dependency relations to the head

In order to use this annotation you need to add the following setting to your Sparv corpus configuration file:

metadata:
  language: eng

For more info on how to use Sparv, check out the Sparv documentation.

Example output:

<token dephead_ref="4" deprel="nsubj" ref="1">This</token>
<token dephead_ref="4" deprel="cop" ref="2">is</token>
<token dephead_ref="4" deprel="det" ref="3">a</token>
<token deprel="root" ref="4">corpus</token>
<token dephead_ref="4" deprel="acl" ref="5">containing</token>
<token dephead_ref="7" deprel="det" ref="6">some</token>
<token dephead_ref="5" deprel="obj" ref="7">words</token>
<token dephead_ref="4" deprel="punct" ref="8">.</token>