bloomberg / koan
A word2vec negative sampling implementation with correct CBOW update.
β260Updated 3 years ago
Related projects β
Alternatives and complementary repositories for koan
- πΈ fastText + Bloom embeddings for compact, full-coverage vectors with spaCyβ287Updated last year
- More interactive weak supervision with FlyingSquidβ315Updated 4 years ago
- Create interactive textual heat maps for Jupiter notebooksβ196Updated 5 months ago
- Misspelling Oblivious Word Embeddingsβ202Updated 5 years ago
- Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddingsβ76Updated 2 years ago
- Labelling platform for text using weak supervision.β260Updated 2 years ago
- Self-Supervision for Named Entity Disambiguation at the Tailβ214Updated 2 years ago
- SummVis is an interactive visualization tool for text summarization.β251Updated 2 years ago
- NeuralQA: A Usable Library for Question Answering on Large Datasets with BERTβ231Updated last year
- π°Natural language processing (NLP) newsletterβ301Updated 4 years ago
- SpikeX - SpaCy Pipes for Knowledge Extractionβ398Updated 3 years ago
- A library to synthesize text datasets using Large Language Models (LLM)β151Updated last year
- LASER multilingual sentence embeddings as a pip packageβ225Updated last year
- Tool for interactive embeddings visualizationβ300Updated 3 months ago
- Deep learning with text doesn't have to be scary.β275Updated last year
- Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.β252Updated 2 years ago
- Neural Searchβ325Updated 5 months ago
- Flexible classic and NeurAl Retrieval Toolkitβ214Updated 4 months ago
- spaCy + UDPipeβ161Updated 2 years ago
- Question-answers, collected from Googleβ124Updated 3 years ago
- Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/β188Updated last year
- β487Updated 9 months ago
- Accelerated NLP pipelines for fast inference on CPU. Built with Transformers and ONNX runtime.β126Updated 3 years ago
- PYthon Automated Term Extractionβ305Updated last year
- Recon NER, Debug and correct annotated Named Entity Recognition (NER) data for inconsistencies and get insights on improving the quality β¦β106Updated 8 months ago
- Self-training with Weak Supervision (NAACL 2021)β157Updated last year
- Toolkit to help understand "what lies" in word embeddings. Also benchmarking!β469Updated last year
- Weakly Supervised End-to-End Learning (NeurIPS 2021)β153Updated last year
- Ensemble topic modelling with pLSAβ112Updated 3 years ago
- Fuzzy matching and more functionality for spaCy.β252Updated 4 months ago