paper-with-me

홈 › Papers

Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features

2023-07-11 · Ester Hlavnova, Sebastian Ruder

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.

📄 PDF Abstract BibTeX arXiv:2307.05454

Code (1)

google-research/multi-morph-checklist 공식 구현

Similar Papers 제목 키워드 기반

DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages

2022-05-24 · Gabriele Sarti, Arianna Bisazza, Ana Guerberof Arenas, Antonio Toral

We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translator…

Machine TranslationNMTTranslation

Does Typological Blinding Impede Cross-Lingual Sharing?

2021-01-28 · EACL 2021 2 · Johannes Bjerva, Isabelle Augenstein

Bridging the performance gap between high- and low-resource languages has been the focus of much previous work. Typological features from databases such as the World Atlas of Language Structures (WALS) are a prime candid…

Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference

2025-08-20 · Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe, Hasan Kurban arxiv

Large language models (LLMs) are increasingly applied in multilingual contexts, yet their capacity for consistent, logically grounded alignment across languages remains underexplored. We present a controlled evaluation f…

Natural Language Inference

Typologically Informed Parameter Aggregation

2026-01-23 · Stef Accou, Wessel Poelman arxiv

Massively multilingual language models enable cross-lingual generalization but underperform on low-resource and unseen languages. While adapter-based fine-tuning offers a parameter-efficient solution, training language-s…

Zero-Shot Cross-Lingual Transfer

What is "Typological Diversity" in NLP?

2024-02-06 · Esther Ploeger, Wessel Poelman, Miryam de Lhoneux, Johannes Bjerva

The NLP research community has devoted increased attention to languages beyond English, resulting in considerable improvements for multilingual NLP. However, these improvements only apply to a small subset of the world's…

DiversityMultilingual NLP