In 2020, the Stanza tool was trained and tested the SUC3 corpus in order to create a high-quality analysis. Currently (in 2024), this analysis is available in Sparv, but it is not provided by default, since it is not fully compatible with SALDO-style lemmas. This model's advantage is that it can be used to lemmatize any token, including out-of-vocabulary tokens.
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:
- <token>:stanza.baseform # Baseform from Stanza
For more info on how to use Sparv, check out the Sparv documentation.
Example output:
<token baseform="det">Det</token>
<token baseform="här">här</token>
<token baseform="vara">är</token>
<token baseform="en">en</token>
<token baseform="korpus">korpus</token>
<token baseform=".">.</token>
Accuracy = 0.99
Stanza: Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton and Christopher D. Manning. 2020
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages. In Association for Computational Linguistics (ACL) System Demonstrations. 2020
SUC3: https://spraakbanken.gu.se/en/resources/suc3