Saved in:
Bibliographic Details
Main Authors: Wu, Xiaoran, Kang, Yipeng
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2109.11408
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911748227858432
author Wu, Xiaoran
Kang, Yipeng
author_facet Wu, Xiaoran
Kang, Yipeng
contents In this paper, we study the technical problem of developing conversational agents that can quickly adapt to unseen tasks, learn task-specific communication tactics, and help listeners finish complex, temporally extended tasks. We find that the uncertainty of language learning can be decomposed to an entropy term and a mutual information term, corresponding to the structural and functional aspect of language, respectively. Combined with reinforcement learning, our method automatically requests human samples for training when adapting to new tasks and learns communication protocols that are succinct and helpful for task completion. Human and simulation test results on a referential game and a 3D navigation game prove the effectiveness of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2109_11408
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Reinforced Natural Language Interfaces via Entropy Decomposition
Wu, Xiaoran
Kang, Yipeng
Human-Computer Interaction
In this paper, we study the technical problem of developing conversational agents that can quickly adapt to unseen tasks, learn task-specific communication tactics, and help listeners finish complex, temporally extended tasks. We find that the uncertainty of language learning can be decomposed to an entropy term and a mutual information term, corresponding to the structural and functional aspect of language, respectively. Combined with reinforcement learning, our method automatically requests human samples for training when adapting to new tasks and learns communication protocols that are succinct and helpful for task completion. Human and simulation test results on a referential game and a 3D navigation game prove the effectiveness of the proposed method.
title Reinforced Natural Language Interfaces via Entropy Decomposition
topic Human-Computer Interaction
url https://arxiv.org/abs/2109.11408