# 3/24 PM ## 論文 * [EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training](https://arxiv.org/abs/2108.01547) * 收集大量從中文社群的文章與對話做成WDC-Dialogue資料集,是目前最大的簡體中文對話資料集。 * 設計對話系統EVA,使用Transformer(bi-directional encoder and uni-directional decoder)作為預訓練模型。 * [CKIP Transformers](https://github.com/ckiplab/ckip-transformers) * 中研院團隊提供的繁體中文的 transformers 模型。 * [Chinese Emotional Dialogue Response Generation via Reinforcement Learning](https://dl.acm.org/doi/abs/10.1145/3446390?casa_token=YLTVREICg-oAAAAA:ijlHeVgfIXh377iD5bZ2r4on-HBKZTvHTsNPgVjVCL7aqUQSb4mcHkA_NIM5l_c_kFNyYTEG59_lEI0) * [EmoSen: Generating Sentiment and Emotion Controlled Responses in a Multimodal Dialogue System](https://ieeexplore.ieee.org/abstract/document/9165162) * [使用GPT2-Chinese生成具有情感的中文對話文字](https://www.cc.ntu.edu.tw/chinese/epaper/0059/20211220_5908.html)
×
Sign in
Email
Password
Forgot password
or
By clicking below, you agree to our
terms of service
.
Sign in via Facebook
Sign in via Twitter
Sign in via GitHub
Sign in via Dropbox
Sign in with Wallet
Wallet (
)
Connect another wallet
New to HackMD?
Sign up