[Adapt] Dialogue Response Ranking Training with Large-Scale Human Feedback Data

[Li Zitong]

Hi Adapters,

This week, I will give you the talk about "Dialogue Response Ranking Training with Large-Scale Human Feedback Data".

Existing open-domain dialog models are generally trained to minimize the perplexity of target human responses. However, some human replies are more engaging than others, spawning more followup interactions. Current conversational models are increasingly capable of producing turns that are context-relevant, but in order to produce compelling agents, these models need to be able to predict and optimize for turns that are genuinely engaging.

In this talk, I will introduce you how to leverage social media feedback data (number of replies and upvotes) to build a large-scale training dataset for feedback prediction. Finally combine the feedback prediction models and a human-like scoring model to rank the machine-generated dialog responses.

I hope my talk makes you feel clear, interesting and helpful.

Time: Wed 4:00pm
Venue: SEIEE 3-414
Best wishes.
Zitong
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20210608/9d046364/attachment.html>