218 Open source projects that are alternatives of or similar to Tongrams

Universal database layer for the client, server & mobile devices. It's like Lego for databases.

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

curated collection of papers for the nlp practitioner 📖👩‍🔬

Empower Sequence Labeling with Task-Aware Language Model

End-to-end ASR/LM implementation with PyTorch

Top-k Approximate String Matching.

Python module (C extension and plain python) implementing Aho-Corasick algorithm

Indonesian Language Models and its Usage

NLP Paper

Self-contained Machine Learning and Natural Language Processing library in Go

Language Model that makes you Laugh .

Korean GPT-2 pretrained cased (KoGPT2)

Language model finetuning on NER with an easy interface, and cross-domain evaluation. We released NER models finetuned on various domain via huggingface model hub.

基于Pytorch和torchtext的自然语言处理深度学习框架。

NEZHA: Neural Contextualized Representation for Chinese Language Understanding

My Reading Lists of Deep Learning and Natural Language Processing

A library & tools to evaluate predictive language models.

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

A Greek edition of BERT pre-trained language model

A Lite Bert For Self-Supervised Learning Language Representations

C++ Implementation of PyTorch Tutorials for Everyone

leetcode.com , algoexpert.io solutions in python and swift

neato compression for key-value data

Open tools and data for cloudless automatic speech recognition

A Mixed Trie and Levenshtein distance implementation in Java for extremely fast prefix string searching and string similarity.

⚡️ Lightning fast URL routing in Python (trie router)

The Capsule Hash Trie Collections Library

Electra pre-trained model using Vietnamese corpus

Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）

Pytorch library for end-to-end transformer models training, inference and serving

A Python wrapper for Kaldi

Concurrent trie-hash map library

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

Get protein embeddings from protein sequences

📖 Some language modeling tools for Keras

An idiomatic and fast QP-trie implementation in pure Rust.

🔑A high performance Key/Value store written in Go with a predictable read/write performance and high throughput. Uses a Bitcask on-disk layout (LSM+WAL) similar to Riak.

Cross-domain NER using cross-domain language modeling, code for ACL 2019 paper

Korean BERT pre-trained cased (KoBERT)

GPT-2 French demo | Démo française de GPT-2

C++ implementation of a fast and memory efficient HAT-trie

Quantize weights and activations in Recurrent Neural Networks.

The implementation of DeBERTa

libgenerics is a minimalistic and generic library for C basic data structures.

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

PyTorch Implementation of OpenAI GPT-2

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

Boilerplate code for quickly getting set up to run language modeling experiments

Google AI 2018 BERT pytorch implementation

Golang Keyword extraction/replacement Datastructure using Tries instead of regexes

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

Pre-training of Deep Bidirectional Transformers for Language Understanding: pre-train TextCNN

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

language model in Chinese，基于Pytorch官方文档实现

🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

TensorFlow GAN implementation using Gumbel Softmax

🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI

A fast and space efficient Radix tree in Java

PhoNLP: A BERT-based multi-task learning toolkit for part-of-speech tagging, named entity recognition and dependency parsing (NAACL 2021)

Minimalistic trie implementation for autosuggest and autocomplete components