SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1901.05415 · 2019

Learning from Dialogue after Deployment: Feed Yourself, Chatbot!

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The majority of conversations a dialogue agent sees over its lifetime occur after it has already been trained and deployed, leaving a vast store of potential training signal untapped. In this work, we propose the self-feeding chatbot, a dialogue agent with the ability to extract new training examples from the conversations it participates in. As our agent engages in conversation, it also estimates user satisfaction in its responses. When the conversation appears to be going well, the user's responses become new training examples to imitate. When the agent believes it has made a mistake, it asks for feedback; learning to predict the feedback that will be given improves the chatbot's dialogue abilities further. On the PersonaChat chit-chat dataset with over 131k training examples, we find that learning from dialogue with a self-feeding chatbot significantly improves performance, regardless of the amount of traditional supervision.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1901.05415")
get_code_for_paper("1901.05415")
have("1901.05415")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1901.05415.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1901.05415.svg)](https://syntology.ai/paper/1901.05415)

Connect an agent — have() is free.