Hellisotherpeople/CX_DB8
a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)
Supports composable embedding architectures—users can combine BERT, ELMo, XLNet, FastText, and domain-specific embeddings like Law2Vec for tailored summarization quality. Operates on PyTorch with Flair as the embedding framework, enabling flexible extraction at word, sentence, or paragraph granularity scored by cosine similarity to query vectors. Outputs summaries as terminal-highlighted text, DOCX files, or interactive 3D visualizations using UMAP or raw embedding components.
230 stars. No commits in the last 6 months.
Stars
230
Forks
26
Language
Python
License
GPL-3.0
Category
Last pushed
Dec 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Hellisotherpeople/CX_DB8"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
langformers/langformers
🚀 Unified NLP Pipelines for Language Models
nlpcloud/nlpcloud-js
NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis,...
EQTPartners/TSDE
TSDE is a novel SSL framework for TSRL, the first of its kind, effectively harnessing a...
will-thompson-k/deeplearning-nlp-models
A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in...
nlpcloud/nlpcloud-php
NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis,...