On the Universality of Deep Contextual Language Models

TL;DR

This paper investigates the concept of universality in deep contextual language models, analyzing their capabilities and limitations across diverse tasks, languages, and domains to guide future research for inclusive NLP applications.

Contribution

It defines seven key dimensions of universality for language models and reviews theoretical and empirical evidence supporting their performance across these dimensions.

Findings

Models perform well across multiple tasks and languages.

Current limitations highlight areas for improvement in fairness and inclusivity.

Survey provides a foundation for future research directions.

Abstract

Deep Contextual Language Models (LMs) like ELMO, BERT, and their successors dominate the landscape of Natural Language Processing due to their ability to scale across multiple tasks rapidly by pre-training a single model, followed by task-specific fine-tuning. Furthermore, multilingual versions of such models like XLM-R and mBERT have given promising results in zero-shot cross-lingual transfer, potentially enabling NLP applications in many under-served and under-resourced languages. Due to this initial success, pre-trained models are being used as `Universal Language Models' as the starting point across diverse tasks, domains, and languages. This work explores the notion of `Universality' by identifying seven dimensions across which a universal model should be able to scale, that is, perform equally well or reasonably well, to be useful across diverse settings. We outline the current theoretical and empirical results that support model performance across these dimensions, along with extensions that may help address some of their current limitations. Through this survey, we lay the foundation for understanding the capabilities and limitations of massive contextual language models and help discern research gaps and directions for future work to make these LMs inclusive and fair to diverse applications, users, and linguistic phenomena.