152 Open source projects that are alternatives of or similar to Keras Language Modeling

Jupyter notebooks for Chainer hands-on

API for the GPT-J language model 🦜. Including a FastAPI backend and a streamlit frontend

Empower Sequence Labeling with Task-Aware Neural Language Model | a PyTorch Tutorial to Sequence Labeling

A GPT-J API to use with python3 to generate text, blogs, code, and more

LSTM Language Model with Subword Units Input Representations

An implementation of Google Brain's 2019 XLNet in PyTorch

An open source implementation of CLIP.

End-to-end ASR/LM implementation with PyTorch

A minimal TF2 re-implementation of the OpenAI GPT training

Data Augmentation for Neural Machine Translation

Implementation for "Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling"

A GPT, made only of MLPs, in Jax

Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing

Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

ICML'2022: Black-Box Tuning for Language-Model-as-a-Service

BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)

Code Generation as a Dual Task of Code Summarization.

The implementation of DeBERTa

Code for the ICLR 2021 paper "A Distributional Approach to Controlled Text Generation"

State of the art Chinese Word Segmentation with Bi-LSTMs

Presenting Collection of Pretrained Models. Links to pretrained models in NLP and voice.

Open tools and data for cloudless automatic speech recognition

Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.

Utility for analyzing Transformer based representations of language.

MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems

Dasher text entry in HTML, CSS, JavaScript, and SVG

End-to-End recipes for pre-training and fine-tuning BERT using Azure Machine Learning Service

Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

NLP Paper

Next Word Prediction using n-gram Probabilistic Model with various Smoothing Techniques

An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"

Multi-label Classification with BERT; Fine Grained Sentiment Analysis from AI challenger

Build a Movie Reviews Sentiment Classifier with Google's BERT Language Model

NLP library designed for reproducible experimentation management

Curated list of all NLP Resources

Google AI 2018 BERT pytorch implementation

Useful resources for Mongolian NLP

BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).

COLING'2020: CoLAKE: Contextualized Language and Knowledge Embedding

Korean BERT pre-trained cased (KoBERT)

Chinese Natural Language Correction via Language Model

The source code of "Language Models are Few-shot Multilingual Learners" (MRL @ EMNLP 2021)

Personalized Query Completion

Connectionist Temporal Classification (CTC) decoder with dictionary and language model for TensorFlow.

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

🐍 Python library for n-gram models in ARPA format

This repo is the home of Romanian Transformers.

A Lite Bert For Self-Supervised Learning Language Representations

machine learning

Code accompanying EMNLP 2018 paper Language Modeling with Sparse Product of Sememe Experts

[ACL‘20] Highway Transformer: A Gated Transformer.

Seq2seq chatbot with attention and anti-language model to suppress generic response, option for further improve by deep reinforcement learning.

Tensorflow with KenLM integrated for beam search scoring

My Reading Lists of Deep Learning and Natural Language Processing

A curated list of NLP resources focused on BERT, attention mechanism, Transformer networks, and transfer learning.

Connectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python.

Korean GPT-2 pretrained cased (KoGPT2)

Streaming based VHDL parser.