• Corpus ID: 252847579

Toward Self-Learning End-to-End Task-oriented Dialog Systems

  title={Toward Self-Learning End-to-End Task-oriented Dialog Systems},
  author={Xiaoying Zhang and Baolin Peng and Jianfeng Gao and Helen M. Meng},
  booktitle={SIGDIAL Conferences},
End-to-end task bots are typically learned over a static and usually limited-size corpus. However, when deployed in dynamic, changing, and open environments to interact with users, task bots tend to fail when confronted with data that deviate from the training corpus, i.e., out-of-distribution samples. In this paper, we study the problem of automatically adapting task bots to changing environments by learning from human-bot interactions with minimum or zero human annotations. We propose SL… 

Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?

This position paper identifies current status and limitations of SF-TOD systems, and explores the WebTOD framework, the alternative direction for building a scalable TOD system when a web/mobile interface is available, powered by a large-scale language model.

SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting

Experimental results on Multiwoz, RADDLE and STAR datasets show that the training-free strategy SGP-TOD, without any task-specific data, yields state-of-the-art (SOTA) zero-shot performance, greatly surpasses the few-shot approaches.

Understanding Causality with Large Language Models: Feasibility and Opportunities

Assessment of the ability of large language models to answer causal questions by analyzing their strengths and weaknesses against three types of causal question and possible future directions and opportunities are discussed.

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

An end-to-end trainable method is proposed that handles new user behaviors at deployment by transferring the dialog to a human agent intelligently and learns online from the human agent’s responses to reduce human agents’ load further.

Iterative policy learning in end-to-end trainable task-oriented neural dialog models

    Bing LiuI. Lane
    Computer Science
    2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
  • 2017
A deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems by jointly optimizing the dialog agent and the user simulator with deep RL by simulating dialogs between the two agents.

SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model

A new method SOLOIST is presented, which uses transfer learning to efficiently build task-oriented dialog systems at scale using a Transformer-based auto-regressive language model, which subsumes different dialog modules into a single neural model.

Continual Learning in Task-Oriented Dialogue Systems

A first-ever continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in both modularized and end-to-end learning settings is proposed and a simple yet effective architectural method based on residual adapters is proposed.

Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning

This paper discusses the advantages of this approach for industry applications of conversational agents, wherein an agent can be rapidly bootstrapped to deploy in front of users and further optimized via interactive learning from actual users of the system.

Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment

Experimental results show that MDS significantly outperforms non-meta-learning baselines and can achieve more than 90% per-turn accuracies with only 10 dialogs on the extended-bAbI dataset.

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

Experimental results show that the end-to-end dialogue agent can learn effectively from the mistake it makes via imitation learning from user teaching, and applying reinforcement learning with user feedback after the imitation learning stage further improves the agent’s capability in successfully completing a task.

A Simple Language Model for Task-Oriented Dialogue

SimpleTOD is a simple approach to task-oriented dialogue that uses a single causal language model trained on all sub-tasks recast as a single sequence prediction problem, which allows it to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2.

Learning from Dialogue after Deployment: Feed Yourself, Chatbot!

On the PersonaChat chit-chat dataset with over 131k training examples, it is found that learning from dialogue with a self-feeding chatbot significantly improves performance, regardless of the amount of traditional supervision.

End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2

This paper presents an end-to-end neural architecture for dialogue systems that addresses both challenges above and achieves the success rate, language understanding, and response appropriateness in the 8th dialogue systems technology challenge (DSTC8).