Flexibly-Structured Model for Task-Oriented Dialogues


    This paper proposes a novel end-to-end architecture for task-oriented dialogue systems. It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot. The policy engine and language generation tasks are modeled jointly following that. The copy-augmented sequential decoder deals with new or unknown values in the conversation, while the multi-label decoder combined with the sequential decoder ensures the explicit assignment of values to slots. On the generation part, slot binary classifiers are used to improve performance. This architecture is scalable to real-world scenarios and is shown through an empirical evaluation to achieve state-of-the-art performance on both the Cambridge Restaurant dataset and the Stanford in-car assistant dataset.


    Lei Shu, Piero Molino, Mahdi Namazifar, Hu Xu, Bing Liu, Huaixiu Zheng, Gokhan Tur

    Full Paper

    ‘Flexibly-Structured Model for Task-Oriented Dialogues’ (PDF)

    Uber AI

    Previous articleImprove User Retention with Causal Learning
    Next articleDSIC: Deep Stereo Image Compression
    Piero Molino
    Piero is a Staff Research Scientist in the Hazy research group at Stanford University. He is a former founding member of Uber AI where he created Ludwig, worked on applied projects (COTA, Graph Learning for Uber Eats, Uber’s Dialogue System) and published research on NLP, Dialogue, Visualization, Graph Learning, Reinforcement Learning and Computer Vision.
    Mahdi Namazifar
    Mahdi Namazifar is a tech lead for Uber's NLP & Conversational AI team.
    Huaixiu Zheng
    Huaixiu Zheng is a senior data scientist at Uber, working on projects in the domains of deep learning, reinforcement learning, natural language processing and conversational AI systems.
    Gokhan Tur
    Gokhan Tur is a Director of Engineering with Uber AI.