MEEP: An Open-Source Platform for Human-Human Dialog Collection and End-to-End Agent Training

10/09/2020
by   Arkady Arkhangorodsky, et al.
0

We create a new task-oriented dialog platform (MEEP) where agents are given considerable freedom in terms of utterances and API calls, but are constrained to work within a push-button environment. We include facilities for collecting human-human dialog corpora, and for training automatic agents in an end-to-end fashion. We demonstrate MEEP with a dialog assistant that lets users specify trip destinations.

READ FULL TEXT
research
06/22/2017

Personalization in Goal-Oriented Dialog

The main goal of modeling human conversation is to create agents which c...
research
04/18/2019

ConvLab: Multi-Domain End-to-End Dialog System Platform

We present ConvLab, an open-source multi-domain end-to-end dialog system...
research
09/20/2021

Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play

Task-oriented dialog systems are often trained on human/human dialogs, s...
research
05/26/2023

DKAF: KB Arbitration for Learning Task-Oriented Dialog Systems with Dialog-KB Inconsistencies

Task-oriented dialog (TOD) agents often ground their responses on extern...
research
05/18/2017

ParlAI: A Dialog Research Software Platform

We introduce ParlAI (pronounced "par-lay"), an open-source software plat...
research
07/17/2019

Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use

Neural end-to-end goal-oriented dialog systems showed promise to reduce ...
research
04/15/2022

Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals

Most dialog systems posit that users have figured out clear and specific...

Please sign up or login with your details

Forgot password? Click here to reset