bentrevett/pytorch-pos-tagging
A tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.
Demonstrates both classical and modern architectures for sequence labeling: a multi-layer BiLSTM baseline using TorchText's data pipeline and pre-trained word embeddings, and fine-tuned transformer models via the Hugging Face transformers library. Integrates spaCy tokenization with PyTorch/TorchText workflows, providing end-to-end training and inference patterns applicable to token-level NLP tasks.
179 stars. No commits in the last 6 months.
Stars
179
Forks
27
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 04, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/bentrevett/pytorch-pos-tagging"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dnanhkhoa/python-vncorenlp
A Python wrapper for VnCoreNLP using a bidirectional communication channel.
ankane/informers
Fast transformer inference for Ruby
datquocnguyen/RDRPOSTagger
A fast and accurate POS and morphological tagging toolkit (EACL 2014)
OpenSextant/SolrTextTagger
A text tagger based on Lucene / Solr, using FST technology
nschneid/arabic-tagger
AQMAR Arabic Tagger: Sequence tagger with cost-augmented structured perceptron training