🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

KenLM: Faster and Smaller Language Model Queries

A function to lookup the language name for a given locale ISO 639-1 code. In data included: english names, native names and directionality.

Source code for ICLR 2018 Paper: Active Learning for Convolutional Neural Networks: A Core-Set Approach

This repository contains code to replicate the no-longer publicly available Toronto BookCorpus dataset

Models, system configurations and outputs of our winning GEC systems in the BEA 2019 shared task described in R. Grundkiewicz, M. Junczys-Dowmunt, K. Heafield: Neural Grammatical Error Correction S…

This project contains a simple Python script that shows a minimal client-side implementation of the Lightstreamer Server Text mode Protocol

An updated version of wmt17-scripts that uses the Nematus Transformer model

Code and model files for the paper: "A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction" (AAAI-18).

ERRor ANnotation Toolkit: Automatically extract and classify grammatical errors in parallel original and corrected sentences.

a simple modification of Chris Dyer's stack LSTM Parser

Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"

Atari - Deep Reinforcement Learning algorithms in TensorFlow

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Sample CodaLab competition for use as a template for SemEval tasks

Text Simplification System and Dataset

The WebSplit Benchmark introducing "Split and Rephrase" task

Data and code used in the 2014 WMT, "Efficient Elicitation of Annotations for Human Evaluation of Machine Translation"

UnseenEst algorithm

Data and code used in the 2015 ACL paper, "Ground Truth for Grammatical Error Correction Metrics"