A Bayesian Framework for Information-Theoretic Probing

09/08/2021
by   Tiago Pimentel, et al.
0

Pimentel et al. (2020) recently analysed probing from an information-theoretic perspective. They argue that probing should be seen as approximating a mutual information. This led to the rather unintuitive conclusion that representations encode exactly the same information about a target task as the original sentences. The mutual information, however, assumes the true probability distribution of a pair of random variables is known, leading to unintuitive results in settings where it is not. This paper proposes a new framework to measure what we term Bayesian mutual information, which analyses information from the perspective of Bayesian agents – allowing for more intuitive findings in scenarios with finite data. For instance, under Bayesian MI we have that data can add information, processing can help, and information can hurt, which makes it more intuitive for machine learning applications. Finally, we apply our framework to probing where we believe Bayesian mutual information naturally operationalises ease of extraction by explicitly limiting the available background knowledge to solve a task.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/09/2021

A Bayesian Nonparametric Estimation of Mutual Information

Mutual information is a widely-used information theoretic measure to qua...
research
10/09/2019

On the Possibility of Rewarding Structure Learning Agents: Mutual Information on Linguistic Random Sets

We present a first attempt to elucidate an Information-Theoretic approac...
research
06/02/2017

Information, Privacy and Stability in Adaptive Data Analysis

Traditional statistical theory assumes that the analysis to be performed...
research
06/07/2022

False Consensus, Information Theory, and Prediction Markets

Our main result shows that when agents' private information about an eve...
research
05/19/2023

Unsupervised Scientific Abstract Segmentation with Normalized Mutual Information

The abstracts of scientific papers consist of premises and conclusions. ...
research
06/27/2012

Ranking by Dependence - A Fair Criteria

Estimating the dependences between random variables, and ranking them ac...
research
10/05/2020

A new Framework for Causal Discovery

Many frameworks exist to infer cause and effect relations in complex non...

Please sign up or login with your details

Forgot password? Click here to reset