Mind the Gap: Assessing Temporal Generalization in Neural Language Models

TL;DR

This paper investigates the limitations of static Transformer-XL language models in predicting future, evolving language data over time, highlighting the need for models that can adapt continuously to maintain performance.

Contribution

It demonstrates that increasing model size alone does not address temporal degradation and introduces the importance of continual updating for language models in dynamic environments.

Findings

Performance degrades over time when predicting future data

Larger models do not inherently solve temporal generalization issues

Continual updating mitigates performance decline

Abstract

Our world is open-ended, non-stationary, and constantly evolving; thus what we talk about and how we talk about it change over time. This inherent dynamic nature of language contrasts with the current static language modelling paradigm, which trains and evaluates models on utterances from overlapping time periods. Despite impressive recent progress, we demonstrate that Transformer-XL language models perform worse in the realistic setup of predicting future utterances from beyond their training period, and that model performance becomes increasingly worse with time. We find that, while increasing model size alone -- a key driver behind recent progress -- does not solve this problem, having models that continually update their knowledge with new information can indeed mitigate this performance degradation over time. Hence, given the compilation of ever-larger language modelling datasets, combined with the growing list of language-model-based NLP applications that require up-to-date factual knowledge about the world, we argue that now is the right time to rethink the static way in which we currently train and evaluate our language models, and develop adaptive language models that can remain up-to-date with respect to our ever-changing and non-stationary world. We publicly release our dynamic, streaming language modelling benchmarks for WMT and arXiv to facilitate language model evaluation that takes temporal dynamics into account.