Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning
- URL: http://arxiv.org/abs/2208.02294v1
- Date: Mon, 25 Jul 2022 16:12:33 GMT
- Title: Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning
- Authors: Deborah Cohen, Moonkyung Ryu, Yinlam Chow, Orgad Keller, Ido
Greenberg, Avinatan Hassidim, Michael Fink, Yossi Matias, Idan Szpektor,
Craig Boutilier, Gal Elidan
- Abstract summary: We develop a real-time, open-ended dialogue system that uses reinforcement learning (RL) to power a bot's conversational skill at scale.
Our work pairs the succinct embedding of the conversation state generated using SOTA (supervised) language models with RL techniques that are particularly suited to a dynamic action space.
- Score: 35.67318830455459
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Despite recent advances in natural language understanding and generation, and
decades of research on the development of conversational bots, building
automated agents that can carry on rich open-ended conversations with humans
"in the wild" remains a formidable challenge. In this work we develop a
real-time, open-ended dialogue system that uses reinforcement learning (RL) to
power a bot's conversational skill at scale. Our work pairs the succinct
embedding of the conversation state generated using SOTA (supervised) language
models with RL techniques that are particularly suited to a dynamic action
space that changes as the conversation progresses. Trained using crowd-sourced
data, our novel system is able to substantially exceeds the (strong) baseline
supervised model with respect to several metrics of interest in a live
experiment with real users of the Google Assistant.
Related papers
- Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations [58.65755268815283]
Many real dialogues are interactive, meaning an agent's utterances will influence their conversational partner, elicit information, or change their opinion.
We use this fact to rewrite and augment existing suboptimal data, and train via offline reinforcement learning (RL) an agent that outperforms both prompting and learning from unaltered human demonstrations.
Our results in a user study with real humans show that our approach greatly outperforms existing state-of-the-art dialogue agents.
arXiv Detail & Related papers (2024-11-07T21:37:51Z) - AutoConv: Automatically Generating Information-seeking Conversations
with Large Language Models [74.10293412011455]
We propose AutoConv for synthetic conversation generation.
Specifically, we formulate the conversation generation problem as a language modeling task.
We finetune an LLM with a few human conversations to capture the characteristics of the information-seeking process.
arXiv Detail & Related papers (2023-08-12T08:52:40Z) - ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented
Instruction Tuning for Digital Human [76.62897301298699]
ChatPLUG is a Chinese open-domain dialogue system for digital human applications that instruction finetunes on a wide range of dialogue tasks in a unified internet-augmented format.
We show that modelname outperforms state-of-the-art Chinese dialogue systems on both automatic and human evaluation.
We deploy modelname to real-world applications such as Smart Speaker and Instant Message applications with fast inference.
arXiv Detail & Related papers (2023-04-16T18:16:35Z) - Lifelong and Continual Learning Dialogue Systems [14.965054800464259]
Book introduces the new paradigm of lifelong learning dialogue systems.
As the systems chat more and more with users or learn more from external sources, they become more knowledgeable and better at conversing.
arXiv Detail & Related papers (2022-11-12T02:39:41Z) - Grounding in social media: An approach to building a chit-chat dialogue
model [9.247397520986999]
Building open-domain dialogue systems capable of rich human-like conversational ability is one of the fundamental challenges in language generation.
Current work on knowledge-grounded dialogue generation primarily focuses on persona incorporation or searching a fact-based structured knowledge source such as Wikipedia.
Our method takes a broader and simpler approach, which aims to improve the raw conversation ability of the system by mimicking the human response behavior on social media.
arXiv Detail & Related papers (2022-06-12T09:01:57Z) - A Mixture-of-Expert Approach to RL-based Dialogue Management [56.08449336469477]
We use reinforcement learning to develop a dialogue agent that avoids being short-sighted (outputting generic utterances) and maximizes overall user satisfaction.
Most existing RL approaches to DM train the agent at the word-level, and thus, have to deal with aly complex action space even for a medium-size vocabulary.
We develop a RL-based DM using a novel mixture of expert language model (MoE-LM) that consists of (i) a LM capable of learning diverse semantics for conversation histories, (ii) a number of specialized LMs (or experts) capable of generating utterances corresponding to a
arXiv Detail & Related papers (2022-05-31T19:00:41Z) - A Review of Dialogue Systems: From Trained Monkeys to Stochastic Parrots [0.0]
We aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans.
We present a broad overview of methods developed to build dialogue systems over the years.
arXiv Detail & Related papers (2021-11-02T08:07:55Z) - Training Conversational Agents with Generative Conversational Networks [74.9941330874663]
We use Generative Conversational Networks to automatically generate data and train social conversational agents.
We evaluate our approach on TopicalChat with automatic metrics and human evaluators, showing that with 10% of seed data it performs close to the baseline that uses 100% of the data.
arXiv Detail & Related papers (2021-10-15T21:46:39Z) - Few-Shot Bot: Prompt-Based Learning for Dialogue Systems [58.27337673451943]
Learning to converse using only a few examples is a great challenge in conversational AI.
The current best conversational models are either good chit-chatters (e.g., BlenderBot) or goal-oriented systems (e.g., MinTL)
We propose prompt-based few-shot learning which does not require gradient-based fine-tuning but instead uses a few examples as the only source of learning.
arXiv Detail & Related papers (2021-10-15T14:36:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.