Continual adaptation for efficient machine communication

11/22/2019
by   Robert D. Hawkins, et al.
0

To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent language models trained with deep neural networks are able to comprehend and produce the existing conventions present in their training data, but are not able to flexibly and interactively adapt those conventions on the fly as humans do. We introduce a repeated reference task as a benchmark for models of adaptation in communication and propose a regularized continual learning framework that allows an artificial agent initialized with a generic language model to more accurately and efficiently communicate with a partner over time. We evaluate this framework through simulations on COCO and in real-time reference game experiments with human partners.

READ FULL TEXT

page 1

page 2

page 4

page 6

page 7

page 8

page 9

page 10

research
12/08/2019

Nonparametric Bayesian Structure Adaptation for Continual Learning

Continual Learning is a learning paradigm where machine learning models ...
research
05/24/2022

Continual-T0: Progressively Instructing 50+ Tasks to Language Models Without Forgetting

Recent work on large language models relies on the intuition that most n...
research
07/18/2020

Drinking from a Firehose: Continual Learning with Web-scale Natural Language

Continual learning systems will interact with humans, with each other, a...
research
03/12/2019

Continual Learning in Practice

This paper describes a reference architecture for self-maintaining syste...
research
05/14/2020

Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning

We present a method for combining multi-agent communication and traditio...
research
12/20/2014

Incremental Adaptation Strategies for Neural Network Language Models

It is today acknowledged that neural network language models outperform ...
research
05/31/2020

Learning to refer informatively by amortizing pragmatic reasoning

A hallmark of human language is the ability to effectively and efficient...

Please sign up or login with your details

Forgot password? Click here to reset