erickrf/nlpnet

A neural network architecture for NLP tasks, using cython for fast performance. Currently, it can perform POS tagging, SRL and dependency parsing.

50
/ 100
Established

Builds on the SENNA architecture with support for both library and command-line usage, accepting raw text or pre-tokenized input across multiple languages (Portuguese and English). The system uses pre-trained models loaded at runtime and outputs structured objects (SRLAnnotatedSentence, ParsedSentence) with token-level attributes accessible for downstream processing. Integrates with NLTK for tokenization and numpy for array operations, with C-compiled performance layers generated via Cython.

408 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

408

Forks

104

Language

Python

License

MIT

Last pushed

Nov 19, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/erickrf/nlpnet"

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