Pith. sign in

REVIEW 4 cited by

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1804.06512 v1 pith:WOFFQIQ4 submitted 2018-04-18 cs.CL

classification cs.CL
keywords learningdialogueagentfeedbackmethodtask-orienteduserend-to-end
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. Efficiency of such learning method may suffer from the mismatch of dialogue state distribution between offline training and online interactive learning stages. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction with users by learning from human teaching and feedback. We design a neural network based task-oriented dialogue agent that can be optimized end-to-end with the proposed learning method. Experimental results show that our end-to-end dialogue agent can learn effectively from the mistake it makes via imitation learning from user teaching. Applying reinforcement learning with user feedback after the imitation learning stage further improves the agent's capability in successfully completing a task.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. How Managers Perceive AI-Assisted Conversational Training for Workplace Communication

    cs.HC 2025-05 conditional novelty 6.0 of 10

    Managers view AI-assisted role-play as useful low-stakes practice for workplace conversations, provided it offers customizable scenarios, actionable feedback, and human-AI teaming.

  2. SIL: Symbiotic Interactive Learning for Language-Conditioned Human-Agent Co-Adaptation

    cs.RO 2025-11 conditional novelty 5.0 of 10

    SIL couples human and robot belief updates in a shared latent space with memory and EWC, reporting 90.4% task completion and ρ≈0.83 alignment.

  3. Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality

    cs.CL 2025-08 conditional novelty 2.0 of 10

    A thesis that combines self-learning from dialog logs, schema-guided prompting, and self-aligned factuality to build task bots with minimal human intervention.

  4. Optimizing Conversational Product Recommendation via Reinforcement Learning

    cs.IR 2025-06 reject novelty 1.0 of 10

    A position paper sketching how RL (DQN, PPO, RLHF) could optimize conversational product recommendation, without any validation.

Pith tools