A minimal implementation of diffusion models for text generation
Topic Modelling for Humans
Pretrained (Language) Models for Probabilistic Time Series Forecasting
Hebrew text generation models based on EleutherAI's gpt-neo
ALIbaba's Collection of Encoder-decoders from MinD
GPT2 for Multiple Languages, including pretrained models
Stuttering Chinese word segmentation
The open-source virtual assistant for Ubuntu based Linux distributions
Basic Utilities for PyTorch Natural Language Processing (NLP)
CakeChat: Emotional Generative Dialog System
Text categorization, arabic language processing, language modeling
Named-entity recognition using neural networks
A large annotated semantic parsing corpus for developing NL interfaces
Software for work with Corpus of Everyday life history Sources
THIS PROJECT MIGRATED TO https://gitlab.com/mwetoolkit/mwetoolkit3/
Construction of Chinese-Korean Bilingual Corpus and Search Technology
a synonym extractor based on web-corpora and a multilingual translator