Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
- nlp
- pre-trained-model
- unilm
- minilm
Repository Index
47,133 repositories indexed
1–20 of 20 · Most stars
Topic Modelling for Humans
- gensim
- topic-modeling
- information-retrieval
- machine-learning
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
- nlp
- embedding
- bert
- ernie
VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media, and works well on texts from other domains.
Module for automatic summarization of text documents and HTML pages.
- python
- lsa
- textteaser
- html-page
A full spaCy pipeline and models for scientific/biomedical documents.
- scientific-documents
- spacy
- custom-pipes
- nlp
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
Natural language detection library for Go
RNNLG is an open source benchmark toolkit for Natural Language Generation (NLG) in spoken dialogue system application domains. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.
- natural-language-processing
- natural-language-generation
- nlg-dataset
- deep-learning
Selected Machine Learning algorithms for natural language processing and semantic analysis in Golang
- go
- golang
- natural-language-processing
- nlp
Implementation of various topic models
A Ruby natural language processor.
- natural-language-processing
- nlp
- ruby
- rubynlp
A natural language understanding system for English
Gibran is an Elixir natural language processor, and a port of WordsCounted.
- natural-language-processing
- nlp
- elixir-lang
Beagle helps you identify keywords, phrases, regexes, and complex search queries of interest in streams of text documents.
- stream-search
- lucene
- luwak
- stored-query-engine
Swift framework for document classification using a Core ML model.
Tagify produces a set of tags from a given source. Source can be either an HTML page, a Markdown document or a plain text. Supports English, Russian, Chinese, Hindi, Spanish, Arabic, Japanese, German, Hebrew, French and Korean languages.
- tagify
- keywords
- keyword-extraction
- html
Term Frequency - Inverse Document Frequency in Ruby
A project around helping to prevent typing typos. TySug (Typo Suggestions) suggests alternative words with respect to keyboard layouts
- string-distance
- suggestions
- typo
- typing
Spelling corrector for Spanish language
- docker
- containers
- go
- spelling-correction