MOSS: End-to-End Dialog System Framework with Modular Supervision

09/12/2019
by   Weixin Liang, et al.
1

A major bottleneck in training end-to-end task-oriented dialog system is the lack of data. To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an encoder-decoder training framework that could incorporate supervision from various intermediate dialog system modules including natural language understanding, dialog state tracking, dialog policy learning, and natural language generation. With only 60 MOSS-all (i.e., MOSS with supervision from all four dialog modules) outperforms state-of-the-art models on CamRest676. Moreover, introducing modular supervision has even bigger benefits when the dialog task has a more complex dialog state and action space. With only 40 outperforms the state-of-the-art model on a complex laptop network troubleshooting dataset, LaptopNetwork, that we introduced. LaptopNetwork consists of conversations between real customers and customer service agents in Chinese. Moreover, MOSS framework can accommodate dialogs that have supervision from different dialog modules at both the framework level and model level. Therefore, MOSS is extremely flexible to update in a real-world deployment.

READ FULL TEXT
research
04/17/2020

Show Us the Way: Learning to Manage Dialog from Demonstrations

We present our submission to the End-to-End Multi-Domain Dialog Challeng...
research
02/03/2023

SPARLING: Learning Latent Representations with Extremely Sparse Activations

Real-world processes often contain intermediate state that can be modele...
research
11/17/2020

Gunrock 2.0: A User Adaptive Social Conversational System

Gunrock 2.0 is built on top of Gunrock with an emphasis on user adaptati...
research
10/13/2016

Gated End-to-End Memory Networks

Machine reading using differentiable reasoning models has recently shown...
research
08/04/2017

A Measure for Dialog Complexity and its Application in Streamlining Service Operations

Dialog is a natural modality for interaction between customers and busin...
research
10/02/2019

Abstractive Dialog Summarization with Semantic Scaffolds

The demand for abstractive dialog summary is growing in real-world appli...
research
02/08/2021

A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining

This paper describes our submission for the End-to-end Multi-domain Task...

Please sign up or login with your details

Forgot password? Click here to reset