# 4/14 PM ## [Zero-Shot Deployment for Cross-Lingual Dialogue System](https://link.springer.com/chapter/10.1007/978-3-030-88483-3_15) * 利用翻譯系統與有較多樣本的語言,來幫助少樣本語言來創建對話系統。 * Noise injection method and multi-task training method。 * 利用翻譯系統從rich-data語言得到目標語言的data,但這目標語言的data因為會有翻譯上的不正確等等問題,作者稱為noise,本篇就是訓練模型去適應noise的data。 ## [EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training](https://arxiv.org/abs/2203.09313) * 之前有看過的EVA的第二版,是簡體中文用的最大的預訓練模型。 ## [TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System](https://arxiv.org/abs/2109.05187) * 還未看完,主要針對多輪對話中,對話主題會變化的問題。 ### 下周進度 * 找GM要報的paper,上面的第三篇是候選。
×
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