erickrf/nlpnet
A neural network architecture for NLP tasks, using cython for fast performance. Currently, it can perform POS tagging, SRL and dependency parsing.
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.
Stars
408
Forks
104
Language
Python
License
MIT
Category
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.
Related tools
nsu-ai/ontonotes-5-parsing
Ontonotes-5-parsing: parser of Ontonotes 5.0 to transform this corpus to a simple JSON format
ikergarcia1996/Basic-CYK-Parser
Basic CYK-Parser written in python 3
LR-POR/PorGram
A Portuguese HPSG Grammar
davidpgero/hungarian-nltk
Simple Hungarian Sentence Analysis with NLTK
busraoguzoglu/CYK-Parser-with-Turkish-CFG
Implementation of CYK algorithm to act as a recognizer and parser with Turkish CFG.