TAPE: Assessing Few-shot Russian Language Understanding

TL;DR

This paper introduces TAPE, a comprehensive benchmark for evaluating Russian language understanding in zero-shot and few-shot scenarios, addressing the lack of standardized evaluation tools for non-English languages.

Contribution

It presents TAPE, a novel benchmark with complex NLU tasks for Russian, including adversarial attacks and subpopulation analysis, to improve robustness and generalization evaluation.

Findings

Simple spelling perturbations significantly impact performance.

Paraphrasing has a negligible effect on model accuracy.

Neural models lag behind human performance on most tasks.

Abstract

Recent advances in zero-shot and few-shot learning have shown promise for a scope of research and practical purposes. However, this fast-growing area lacks standardized evaluation suites for non-English languages, hindering progress outside the Anglo-centric paradigm. To address this line of research, we propose TAPE (Text Attack and Perturbation Evaluation), a novel benchmark that includes six more complex NLU tasks for Russian, covering multi-hop reasoning, ethical concepts, logic and commonsense knowledge. The TAPE's design focuses on systematic zero-shot and few-shot NLU evaluation: (i) linguistic-oriented adversarial attacks and perturbations for analyzing robustness, and (ii) subpopulations for nuanced interpretation. The detailed analysis of testing the autoregressive baselines indicates that simple spelling-based perturbations affect the performance the most, while paraphrasing the input has a more negligible effect. At the same time, the results demonstrate a significant gap between the neural and human baselines for most tasks. We publicly release TAPE (tape-benchmark.com) to foster research on robust LMs that can generalize to new tasks when little to no supervision is available.