TAPE: Assessing Few-shot Russian Language Understanding

Ekaterina Taktasheva, Tatiana Shavrina, Alena Fenogenova, Denis Shevelev, Nadezhda Katricheva, Maria Tikhonova, Albina Akhmetgareeva, Oleg Zinkevich, Anastasiia Bashmakova, Svetlana Iordanskaia, Alena Spiridonova, Valentina Kurenshchikova, Ekaterina Artemova, Vladislav Mikhailov


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 (https://tape-benchmark.com) to foster research on robust LMs that can generalize to new tasks when little to no supervision is available.
Anthology ID:
2022.findings-emnlp.183
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2472–2497
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.183
DOI:
10.18653/v1/2022.findings-emnlp.183
Bibkey:
Cite (ACL):
Ekaterina Taktasheva, Tatiana Shavrina, Alena Fenogenova, Denis Shevelev, Nadezhda Katricheva, Maria Tikhonova, Albina Akhmetgareeva, Oleg Zinkevich, Anastasiia Bashmakova, Svetlana Iordanskaia, Alena Spiridonova, Valentina Kurenshchikova, Ekaterina Artemova, and Vladislav Mikhailov. 2022. TAPE: Assessing Few-shot Russian Language Understanding. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2472–2497, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
TAPE: Assessing Few-shot Russian Language Understanding (Taktasheva et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.183.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.183.mp4