neuml / magnitude
Magnitude fork that only supports Word2Vec, GloVe and fastText embeddings
☆12Updated 4 years ago
Related projects: ⓘ
- 🦀 A Rust implementation of a RoBERTa classification model for the SNLI dataset☆12Updated 3 years ago
- ☆29Updated 2 years ago
- ☆70Updated last year
- 💫 A spaCy package for Yohei Tamura's Rust tokenizations library☆27Updated 10 months ago
- 🌸 Train floret vectors☆18Updated last year
- FAST is an annotation tool that focuses on mobile devices. https://aclanthology.org/2021.emnlp-demo.41/☆53Updated 2 years ago
- allennlp-light is a port of AllenNLP's core modules and nn portions into a standalone package with minimum dependencies☆52Updated last year
- ALMa (Active Learning Manager) Keeps track of labeled and unlabeled data for active learning☆42Updated 4 years ago
- Language detection using Spacy and Fasttext☆53Updated 9 months ago
- Japanese tutorial for Vespa☆20Updated 6 years ago
- spaCy entry points for Curated Transformers☆23Updated 2 weeks ago
- Reverse engineer patterns for use with SpaCy's DependencyMatcher☆34Updated 4 years ago
- Benchmark for Japanese document embedding & vector search☆28Updated 6 months ago
- Vespa application making an index of the CORD-19 dataset.☆39Updated 2 weeks ago
- A file utility for accessing both local and remote files through a unified interface.☆36Updated last month
- Python implementation of "Data-dependent Learning of Symmetric/Antisymmetric Relations for Knowledge Base Completion [Manabe+. 2018]"☆11Updated 6 years ago
- Visualization of Natural Language Processing for React☆17Updated 6 years ago
- SDK for TEASPN, a framework and a protocol for integrated writing assistance environments☆61Updated last year
- An asynchronous concurrent pipeline for classifying Common Crawl based on fastText's pipeline.☆85Updated 3 years ago
- A python library for automatic semantic graph generation from human-readable text.☆27Updated 5 years ago
- Official details for: [1803.08493] Context is Everything: Finding Meaning Statistically in Semantic Spaces☆39Updated 5 years ago
- 🧬 A VS Code extension for annotating data with Prodigy☆30Updated 2 years ago
- Python library to work with ConceptNet offline☆10Updated last year
- fastlangid, the only language identification package that support cantonese (zh-yue), simplified (zh-hans) and traditional chinese (zh-ha…☆38Updated last year
- Python SDK for the TextRazor Text Analytics API☆20Updated last year
- Generate a SQLite database from Wikipedia & Wikidata dumps.☆30Updated 5 months ago
- Finds linguistic patterns effortlessly☆31Updated last year
- Cortex-compatible model server for Python and TensorFlow☆16Updated last year
- Code for "Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem" (NAACL 2022)☆92Updated 2 years ago
- Rust library providing fast language model queries in compressed space☆23Updated last year