yuanxiaosc/BERT-for-Sequence-Labeling-and-Text-Classification

This is the template code to use BERT for sequence lableing and text classification, in order to facilitate BERT for more tasks. Currently, the template code has included conll-2003 named entity identification, Snips Slot Filling and Intent Prediction.

50
/ 100
Established

Built on TensorFlow with Google's pretrained BERT model, this template supports both sequence labeling and text classification through fine-tuning, with optional LSTM layers for joint intent/slot tasks. Pre-trained checkpoints and inference scripts are provided for immediate use on ATIS and Snips datasets, while custom tasks can be added by implementing a DataProcessor subclass and registering it in the main pipeline.

471 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

471

Forks

96

Language

Python

License

Apache-2.0

Last pushed

Dec 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yuanxiaosc/BERT-for-Sequence-Labeling-and-Text-Classification"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.