bloomberg / koan
A word2vec negative sampling implementation with correct CBOW update.
☆260Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for koan
- 🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy☆287Updated last year
- More interactive weak supervision with FlyingSquid☆315Updated 4 years ago
- Create interactive textual heat maps for Jupiter notebooks☆196Updated 5 months ago
- Misspelling Oblivious Word Embeddings☆202Updated 5 years ago
- Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings☆76Updated 2 years ago
- Labelling platform for text using weak supervision.☆260Updated 2 years ago
- Self-Supervision for Named Entity Disambiguation at the Tail☆214Updated 2 years ago
- SummVis is an interactive visualization tool for text summarization.☆251Updated 2 years ago
- NeuralQA: A Usable Library for Question Answering on Large Datasets with BERT☆231Updated last year
- 📰Natural language processing (NLP) newsletter☆301Updated 4 years ago
- SpikeX - SpaCy Pipes for Knowledge Extraction☆398Updated 3 years ago
- A library to synthesize text datasets using Large Language Models (LLM)☆151Updated last year
- LASER multilingual sentence embeddings as a pip package☆225Updated last year
- Tool for interactive embeddings visualization☆300Updated 3 months ago
- Deep learning with text doesn't have to be scary.☆275Updated last year
- Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.☆252Updated 2 years ago
- Neural Search☆325Updated 5 months ago
- Flexible classic and NeurAl Retrieval Toolkit☆214Updated 4 months ago
- spaCy + UDPipe☆161Updated 2 years ago
- Question-answers, collected from Google☆124Updated 3 years ago
- Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/☆188Updated last year
- ☆487Updated 9 months ago
- Accelerated NLP pipelines for fast inference on CPU. Built with Transformers and ONNX runtime.☆126Updated 3 years ago
- PYthon Automated Term Extraction☆305Updated last year
- Recon NER, Debug and correct annotated Named Entity Recognition (NER) data for inconsistencies and get insights on improving the quality …☆106Updated 8 months ago
- Self-training with Weak Supervision (NAACL 2021)☆157Updated last year
- Toolkit to help understand "what lies" in word embeddings. Also benchmarking!☆469Updated last year
- Weakly Supervised End-to-End Learning (NeurIPS 2021)☆153Updated last year
- Ensemble topic modelling with pLSA☆112Updated 3 years ago
- Fuzzy matching and more functionality for spaCy.☆252Updated 4 months ago