XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning
This addresses the need for challenging benchmarks to advance machine reasoning and cross-lingual transfer in NLP, though it is incremental as it builds on existing dataset concepts.
The authors introduced XCOPA, a multilingual dataset for causal commonsense reasoning across 11 languages, including resource-poor ones, and found that current multilingual models underperform compared to translation-based methods, with proposed adaptation strategies showing improvements over random baselines.
In order to simulate human language capacity, natural language processing systems must be able to reason about the dynamics of everyday situations, including their possible causes and effects. Moreover, they should be able to generalise the acquired world knowledge to new languages, modulo cultural differences. Advances in machine reasoning and cross-lingual transfer depend on the availability of challenging evaluation benchmarks. Motivated by both demands, we introduce Cross-lingual Choice of Plausible Alternatives (XCOPA), a typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages, which includes resource-poor languages like Eastern Apurímac Quechua and Haitian Creole. We evaluate a range of state-of-the-art models on this novel dataset, revealing that the performance of current methods based on multilingual pretraining and zero-shot fine-tuning falls short compared to translation-based transfer. Finally, we propose strategies to adapt multilingual models to out-of-sample resource-lean languages where only a small corpus or a bilingual dictionary is available, and report substantial improvements over the random baseline. The XCOPA dataset is freely available at github.com/cambridgeltl/xcopa.