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

By Weixin Liang, Youzhi Tian, Chengcai Chen, Zhou Yu. 2019

55 citations recorded by the source corpus.

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% of the training data, 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% of the training data, MOSS-all outperforms the state-of-the-art model on a complex laptop network trouble shooting 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 framework level and model level. Therefore, MOSS is extremely flexible to update in real-world deployment.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

ALICE: Active Learning with Contrastive Natural Language Explanations (2020, background): “However, previous work neglects the fact that there is usually a limited time budget to interact with domain experts (e.g., medical experts, biologists) (Liang et al., 2019, 2020) and high-quality natural language explanations are expensive, by nature.”
A Simple Language Model for Task-Oriented Dialogue (2020, background): “[25] trained language understanding, dialogue state tracking, and dialogue policy modules with a shared encoder.”
Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation (2020, background): “Currently, both academia and industry (Ram et al., 2018a; Li et al., 2019b; Liang et al., 2019) rely on human ratings to evaluate open-domain dialogs.”
Learning to Annotate: Modularizing Data Augmentation for Text Classifiers with Natural Language Explanations (2019, background): “Liang et al. (2019) explore proposed Modular Supervision Network to incorporate supervision from various intermediate dialog system modules at both framework level and model level.”