Evaluation Benchmarks for Spanish Sentence Representations
This work addresses the need for standardized benchmarks to evaluate Spanish language models, enabling fairer and more comparable assessments, though it is incremental as it adapts existing English benchmarks to Spanish.
The authors tackled the lack of systematic evaluation resources for Spanish pre-trained language models by building two benchmarks, Spanish SentEval and Spanish DiscoEval, which include pre-existing and newly constructed datasets to assess sentence representations, and they evaluated recent models, finding that mBERT often provides richer representations for discourse tasks.
Due to the success of pre-trained language models, versions of languages other than English have been released in recent years. This fact implies the need for resources to evaluate these models. In the case of Spanish, there are few ways to systematically assess the models' quality. In this paper, we narrow the gap by building two evaluation benchmarks. Inspired by previous work (Conneau and Kiela, 2018; Chen et al., 2019), we introduce Spanish SentEval and Spanish DiscoEval, aiming to assess the capabilities of stand-alone and discourse-aware sentence representations, respectively. Our benchmarks include considerable pre-existing and newly constructed datasets that address different tasks from various domains. In addition, we evaluate and analyze the most recent pre-trained Spanish language models to exhibit their capabilities and limitations. As an example, we discover that for the case of discourse evaluation tasks, mBERT, a language model trained on multiple languages, usually provides a richer latent representation than models trained only with documents in Spanish. We hope our contribution will motivate a fairer, more comparable, and less cumbersome way to evaluate future Spanish language models.