guillaumegenthial/sequence_tagging
A TensorFlow implementation of Named Entity Recognition using bi-directional LSTM with CRF decoding and GloVe embeddings.
Not currently ranked — collecting fresh signals.
star history
This repository provides a sequence labeling model for Named Entity Recognition using character-level and word-level embeddings processed through bidirectional LSTM layers, with a linear-chain CRF for decoding. The model concatenates character-based word representations with pre-trained GloVe vectors to capture both morphological and semantic features, achieving F1 scores between 90 and 91 on standard benchmarks.
Frequently asked
- What is guillaumegenthial/sequence_tagging?
- A TensorFlow implementation of Named Entity Recognition using bi-directional LSTM with CRF decoding and GloVe embeddings.
- Is sequence_tagging open source?
- Yes — guillaumegenthial/sequence_tagging is open source, released under the Apache-2.0 license.
- What language is sequence_tagging written in?
- guillaumegenthial/sequence_tagging is primarily written in Python.
- How popular is sequence_tagging?
- guillaumegenthial/sequence_tagging has 2k stars on GitHub.
- Where can I find sequence_tagging?
- guillaumegenthial/sequence_tagging is on GitHub at https://github.com/guillaumegenthial/sequence_tagging.