fandongmeng

DTMT_InDec

Implementation of DTMT with incremental decoding

StackedDTMT

Stacked Encoder Enhanced Deep Transition RNMT

Multi_Unit_Transformer

RSI-NAT

Source code for "Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation"

awesome-multimodal-ml

Reading list for research topics in multimodal machine learning

bert

TensorFlow code and pre-trained models for BERT

BMI-NMT

CapsNet-Tensorflow

A Tensorflow implementation of CapsNet(Capsules Net) in Hinton's paper Dynamic Routing Between Capsules

CBMI

ClidSum

ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization

ColossalAI

Colossal-AI: A Unified Deep Learning System for Large-Scale Parallel Training

Cross-Domain_NER

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

fandongmeng.github.com

My online resume

GCDT

Code for the paper: GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling

graph-one

MSCTD

Code and Data for the ACL22 main conference paper "MSCTD: A Multimodal Sentiment Chat Translation Dataset"

MTBook

《机器翻译：基础与模型》肖桐 朱靖波 著 - Machine Translation: Foundations and Models

nmt_adequacy

nmtpytorch

Sequence-to-Sequence Framework in PyTorch

OR-NMT

Source code for the paper <Bridging the Gap between Training and Inference for Neural Machine Translation>

sha-rnn

Single Headed Attention RNN - "Stop thinking with your head"

sparse-and-robust-PLM

[NeurIPS 2022] "A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models", Yuanxin Liu, Fandong Meng, Zheng Lin, Jiangnan Li, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou

tf_ner

Simple and Efficient Tensorflow implementations of NER models with tf.estimator and tf.data

TLAT-NMT

Source code for the EMNLP 2020 long paper <Token-level Adaptive Training for Neural Machine Translation>.

transformer-xl

TurboTransformers

a fast and user-friendly tool for transformer inference on CPU and GPU

WeChat-TFCC

wenmt

nmt models

WeTS

A benchmark for the task of translation suggestion

wit

WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.