Code and data accompanying the paper "TRUE: Re-evaluating Factual Consistency Evaluation".

Multilingual extension of T0

Open-Domain Question Answering Goes Conversational via Question Rewriting

Google Research

Minimalist NMT for educational purposes

Data and code for Knowledge-Based Machine Translation Evaluation (KoBE)

Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)

Yet Another (natural language) Parser

A very simple framework for state-of-the-art Natural Language Processing (NLP)

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.

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

NMT domain adaptation papers (updating...)

State-of-the-Art Text Embeddings

A tool for holistic analysis of language generations systems

Domain Adaptation of Neural Machine Translation by Lexicon Induction

A python package for sampling from determinantal point processes

XLNet for generating language.

Machine Learning applied to Natural Language Processing Toolkit used in the Lisbon Machine Learning Summer School

KenLM: Faster and Smaller Language Model Queries

Scripts to compute moore-lewis using kenlm

TensorFlow code and pre-trained models for BERT

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

A library for efficient similarity search and clustering of dense vectors.

Approximate Nearest Neighbor Search for Sparse Data in Python!

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Unsupervised text tokenizer for Neural Network-based text generation.