ypengc7512

dataset

Multi30k Dataset

lxmert

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".

MASS

MASS: Masked Sequence to Sequence Pre-training for Language Generation

MUSE

A library for Multilingual Unsupervised or Supervised word Embeddings

PLMpapers

Must-read Papers on pre-trained language models.

pytorch-doc-zh

Pytorch 中文文档

transformers

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

vilbert_beta

visualbert

Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

Zh-Ja-Translation-Corpus

从人民网收集中日对译语料库/「人民网」から日中対訳コーパスを収集する

Adaptive-Diversity-Promoting

Adversarial Defense for Ensemble Models (ICML 2019)

BERT-related-papers

BERT-related papers

Conference-Acceptance-Rate

Statistics of acceptance rate for the main AI conference

dlcl

The implementation of "Learning Deep Transformer Models for Machine Translation"

dspdfviewer

Dual-Screen PDF Viewer for latex-beamer

DualRL

A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

MomentumContrast.pytorch

Reproduction of Momentum Contrast for Unsupervised Visual Representation Learning

mosesdecoder

Moses, the machine translation system

MT-Reading-List

A machine translation reading list maintained by Tsinghua Natural Language Processing Group

paws

This dataset contains 108,463 human-labeled and 656k noisily labeled pairs that feature the importance of modeling structure, context, and word order information for the problem of paraphrase identification.

selective-attn

Data and code used in our NAACL'19 paper "Selective Attention for Context-aware Neural Machine Translation"

self-critical.pytorch

Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning; py3 version in py3 branch (it actually should be compatible to both py2 and py3)

sparsemax-pytorch

Implementation of Sparsemax activation in Pytorch

SU4MLC

Code for the article "Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification" (EMNLP 2018)

Tatoeba-Challenge

THUMT

An open-source neural machine translation toolkit developed by Tsinghua Natural Language Processing Group

transformer

A TensorFlow Implementation of the Transformer: Attention Is All You Need

Unsupervised_Embedding_Learning

Code for Unsupervised Embedding Learning via Invariant and Spreading Instance Feature