IntelLabs/nlp-architect
A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks
Archived**⚠️ NOTE: This project is discontinued and no longer maintained by Intel. It has known security vulnerabilities.** Provides modular NLP/NLU models for sequence tagging (NER, chunking), dependency parsing, intent detection, sentiment analysis, and semantic tasks like aspect-based sentiment analysis and relation identification. Supports multi-framework training with TensorFlow, PyTorch, and DyNet through a framework-agnostic API, with built-in optimization techniques including 8-bit BERT quantization and knowledge distillation. Includes end-to-end solutions for term expansion and trend analysis, plus utilities for text preprocessing, embeddings, and dataset loading.
2,935 stars. No commits in the last 6 months.
Stars
2,935
Forks
443
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IntelLabs/nlp-architect"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
minggnim/nlp-models
A repository for training transformer based models
yuanzhoulvpi2017/zero_nlp
中文nlp解决方案(大模型、数据、模型、训练、推理)
LoicGrobol/zeldarose
Train transformer-based models.
CPJKU/wechsel
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of...
soldni/pyterrier_sentence_transformers
Create PyTerrier compatible dense indices using any sentence_transformers model