XNLIeu: a dataset for cross-lingual NLI in Basque
This work addresses the problem of low-resource language support in NLU for Basque, but it is incremental as it extends an existing benchmark with a new language.
The authors tackled the lack of cross-lingual Natural Language Inference (NLI) resources for Basque by creating XNLIeu, a dataset developed via machine translation and manual post-edition, and found that translate-train strategies yield better results, though gains are lower on natively built datasets.
XNLI is a popular Natural Language Inference (NLI) benchmark widely used to evaluate cross-lingual Natural Language Understanding (NLU) capabilities across languages. In this paper, we expand XNLI to include Basque, a low-resource language that can greatly benefit from transfer-learning approaches. The new dataset, dubbed XNLIeu, has been developed by first machine-translating the English XNLI corpus into Basque, followed by a manual post-edition step. We have conducted a series of experiments using mono- and multilingual LLMs to assess a) the effect of professional post-edition on the MT system; b) the best cross-lingual strategy for NLI in Basque; and c) whether the choice of the best cross-lingual strategy is influenced by the fact that the dataset is built by translation. The results show that post-edition is necessary and that the translate-train cross-lingual strategy obtains better results overall, although the gain is lower when tested in a dataset that has been built natively from scratch. Our code and datasets are publicly available under open licenses.