SocioProbe: What, When, and Where Language Models Learn about Sociodemographics

11/08/2022
by   Anne Lauscher, et al.
0

Pre-trained language models (PLMs) have outperformed other NLP models on a wide range of tasks. Opting for a more thorough understanding of their capabilities and inner workings, researchers have established the extend to which they capture lower-level knowledge like grammaticality, and mid-level semantic knowledge like factual understanding. However, there is still little understanding of their knowledge of higher-level aspects of language. In particular, despite the importance of sociodemographic aspects in shaping our language, the questions of whether, where, and how PLMs encode these aspects, e.g., gender or age, is still unexplored. We address this research gap by probing the sociodemographic knowledge of different single-GPU PLMs on multiple English data sets via traditional classifier probing and information-theoretic minimum description length probing. Our results show that PLMs do encode these sociodemographics, and that this knowledge is sometimes spread across the layers of some of the tested PLMs. We further conduct a multilingual analysis and investigate the effect of supplementary training to further explore to what extent, where, and with what amount of pre-training data the knowledge is encoded. Our overall results indicate that sociodemographic knowledge is still a major challenge for NLP. PLMs require large amounts of pre-training data to acquire the knowledge and models that excel in general language understanding do not seem to own more knowledge about these aspects.

READ FULL TEXT

page 5

page 7

research
12/03/2021

Probing Linguistic Information For Logical Inference In Pre-trained Language Models

Progress in pre-trained language models has led to a surge of impressive...
research
05/16/2023

Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models

Memory is one of the most essential cognitive functions serving as a rep...
research
09/11/2022

Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation Analysis

To what extent do pre-trained language models grasp semantic knowledge r...
research
04/12/2022

A Review on Language Models as Knowledge Bases

Recently, there has been a surge of interest in the NLP community on the...
research
05/27/2021

Inspecting the concept knowledge graph encoded by modern language models

The field of natural language understanding has experienced exponential ...
research
07/28/2022

Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions

Large amounts of training data are one of the major reasons for the high...
research
01/25/2022

Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language

With the methodological support of probing (or diagnostic classification...

Please sign up or login with your details

Forgot password? Click here to reset