Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention

Negar Foroutan, Mohammadreza Banaei, Karl Aberer, Antoine Bosselut


Abstract
In this work, we study whether multilingual language models (MultiLMs) can transfer logical reasoning abilities to other languages when they are fine-tuned for reasoning in a different language. We evaluate the cross-lingual reasoning abilities of MultiLMs in two schemes: (1) where the language of the context and the question remain the same in the new languages that are tested (i.e., the reasoning is still monolingual, but the model must transfer the learned reasoning ability across languages), and (2) where the language of the context and the question is different (which we term code-switched reasoning). On two logical reasoning datasets, RuleTaker and LeapOfThought, we demonstrate that although MultiLMs can transfer reasoning ability across languages in a monolingual setting, they struggle to transfer reasoning abilities in a code-switched setting. Following this observation, we propose a novel attention mechanism that uses a dedicated set of parameters to encourage cross-lingual attention in code-switched sequences, which improves the reasoning performance by up to 14% and 4% on the RuleTaker and LeapOfThought datasets, respectively.
Anthology ID:
2023.findings-emnlp.632
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9422–9442
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.632
DOI:
10.18653/v1/2023.findings-emnlp.632
Bibkey:
Cite (ACL):
Negar Foroutan, Mohammadreza Banaei, Karl Aberer, and Antoine Bosselut. 2023. Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9422–9442, Singapore. Association for Computational Linguistics.
Cite (Informal):
Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention (Foroutan et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.632.pdf