Sequence Tagger for Partially Annotated Dataset in spaCy
Project description
spacy-partial-tagger
This is a CRF tagger for partially annotated dataset in spaCy. The implementation of this tagger is based on Effland and Collins. (2021).
Dataset
Prepare spaCy binary format file. This library expects tokenization is character-based. For more detail about spaCy binary format, see this page.
Training
python -m spacy train config.cfg --output outputs --paths.train train.spacy --paths.dev dev.spacy
Evaluation
python -m spacy evaluate outputs/model-best test.spacy
Installation
pip install spacy-partial-tagger
References
- Thomas Effland and Michael Collins. 2021. Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss. Transactions of the Association for Computational Linguistics, 9:1320–1335.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
spacy-partial-tagger-0.8.0.tar.gz
(11.9 kB
view hashes)
Built Distribution
Close
Hashes for spacy-partial-tagger-0.8.0.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 03edf4669b887fe563e537cfc1b45f14235dae340bcb0c3e24a20eec8f730b6a |
|
MD5 | 34b440e2b0c023a3a1603a06852f98ef |
|
BLAKE2b-256 | 434cdca90ff7ffa9a2247252ff86a9ec97ad8f233fa4ca1d22bc8ecf5b2a524a |
Close
Hashes for spacy_partial_tagger-0.8.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7eb5f8fa1492e6e0937811939d935949098dc0174637a4a53e905b3816903d29 |
|
MD5 | cd11f4709b45e5dfc6caef011b5599b7 |
|
BLAKE2b-256 | aa1647baee58cbde7a43656e1bf2f22f8e734582fc35069ae8946415cc6c0394 |