Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features
This addresses the challenge of developing robust NLP systems for global languages, though it is incremental as it builds on existing testing methods.
The paper tackled the problem of understanding how NLP models generalize to typologically diverse languages by proposing M2C, a framework for behavioral testing, and found that while models perform well in English, they fail on specific typological features like temporal expressions in Swahili and compounding possessives in Finnish.
A challenge towards developing NLP systems for the world's languages is understanding how they generalize to typological differences relevant for real-world applications. To this end, we propose M2C, a morphologically-aware framework for behavioral testing of NLP models. We use M2C to generate tests that probe models' behavior in light of specific linguistic features in 12 typologically diverse languages. We evaluate state-of-the-art language models on the generated tests. While models excel at most tests in English, we highlight generalization failures to specific typological characteristics such as temporal expressions in Swahili and compounding possessives in Finish. Our findings motivate the development of models that address these blind spots.