Bird, Steven, Edward Loper and Ewan Klein (2009), Natural Language Processing with Python. O’Reilly Media Inc.
The sentence segmenter is based on NLTK's PunktWordTokenizer. Sparv's version is custom-made for Swedish by supplying a model built on StorSUC. It is, however, possible to configure the sentence segmenter for other languages.
This analysis is used with Sparv. Check out Sparv's quick start guide to get started!
To use this analysis, add the following line under export.annotations in the Sparv corpus configuration file:
- segment.sentence # Sentence segments
For more info on how to use Sparv, check out the Sparv documentation.
Example output:
<sentence>
<token>Det</token>
<token>här</token>
<token>är</token>
<token>en</token>
<token>korpus</token>
<token>.</token>
</sentence>
<sentence>
<token>Den</token>
<token>har</token>
<token>flera</token>
<token>meningar</token>
<token>.</token>
</sentence>