chenyangh

cascaded-generation

Cascaded Text Generation with Markov Transformers

CBET-dataset

Cleaned Balanced Emotional Tweets (CBET) Dataset

chenyangh

CNAT

Non-autoregressive Translation by Learning Target Categorical Codes

DialogueGenerationWithEmotion

Response generation giving specific emotion.

DSLP

Deeply Supervised, Layer-wise Prediction-aware (DSLP) Transformer for Non-autoregressive Neural Machine Translation

SemEval2019Task3

Code for ANA at SemEval-2019 Task 3

SentimentAnalysis

This project aims at learning sentiment features from user reviews

Seq2Emo

Sequence to multi-label emotion classification

TAG-waTer_pAper_nameoloGy

TAG: waTer pAper nameoloGy

chenyangh/DSLP

Deeply Supervised, Layer-wise Prediction-aware (DSLP) Transformer for Non-autoregressive Neural Machine Translation

chenyangh/chenyangh

chenyangh/CNAT

Non-autoregressive Translation by Learning Target Categorical Codes

chenyangh/Emotionator

The best emotion detector on this planet 🌍

chenyangh/mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

chenyangh/sacrebleu

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

chenyangh/U-2-Net

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

chenyangh/vision_transformer

chenyangh/Awesome-Text-Diffusion-Models

[IJCAI'23] The official Github page of the paper "Diffusion Models for Non-autoregressive Text Generation: A Survey".

chenyangh/BANG

BANG is a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generation can be uniformly regarded as to what extent previous tokens can be attended, and BANG bridges AR and NAR generation by designing a novel model structure for large-scale pretraining. The pretrained BANG model can simultaneously support AR, NAR and semi-NAR generation to meet different requirements.

chenyangh/benchmarks

Collection of benchmarks written by researchers at Amii

chenyangh/chenyangh.github.io

A beautiful, simple, clean, and responsive Jekyll theme for academics

chenyangh/CMLMC

Code for the ICLR'22 paper "Improving Non-Autoregressive Translation Models Without Distillation"

chenyangh/DAT-Length-Control

chenyangh/eflomal

Efficient Low-Memory Aligner

chenyangh/esm

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

chenyangh/fairseq-1

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

chenyangh/fairseq2

FAIR Sequence Modeling Toolkit 2

chenyangh/Fully-NAT

chenyangh/giza-py

A simple, Python-based, command-line runner for MGIZA++.

chenyangh/GLUE-baselines

[DEPRECATED] Repo for exploring multi-task learning approaches to learning sentence representations

chenyangh/GMA

Code for ACL 2022 findings paper "Gaussian Multi-head Attention for Simultaneous Machine Translation"

chenyangh/MoE-Waitk

Code for EMNLP 2021 oral paper "Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy"

chenyangh/NAG-BERT

[EACL'21] Non-Autoregressive with Pretrained Language Model

chenyangh/OTTAWA

chenyangh/POINTER

chenyangh/pytorch-struct

Fast, general, and tested differentiable structured prediction in PyTorch

chenyangh/REDER

[NeurIPS 2021] Duplex Sequence-to-Sequence Learning for Reversible Machine Translation

chenyangh/tensor2struct-public

Semantic parsers based on encoder-decoder framework

chenyangh/terashuf

terashuf shuffles multi-terabyte text files using limited memory