paper-with-me

홈 › Papers

Generalization Measures for Zero-Shot Cross-Lingual Transfer

2024-04-24 · Saksham Bassi, Duygu Ataman, Kyunghyun Cho

A model's capacity to generalize its knowledge to interpret unseen inputs with different characteristics is crucial to build robust and reliable machine learning systems. Language model evaluation tasks lack information metrics about model generalization and their applicability in a new setting is measured using task and language-specific downstream performance, which is often lacking in many languages and tasks. In this paper, we explore a set of efficient and reliable measures that could aid in computing more information related to the generalization capability of language models in cross-lingual zero-shot settings. In addition to traditional measures such as variance in parameters after training and distance from initialization, we also measure the effectiveness of sharpness in loss landscape in capturing the success in cross-lingual transfer and propose a novel and stable algorithm to reliably compute the sharpness of a model optimum that correlates to generalization.

📄 PDF Abstract BibTeX arXiv:2404.15928

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual TransferLanguage Model EvaluationLanguage ModelingLanguage ModellingZero-Shot Cross-Lingual Transfer

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Zero-shot Cross-lingual Transfer is Under-specified Optimization

2022-07-12 · RepL4NLP (ACL) 2022 5 · Shijie Wu, Benjamin Van Durme, Mark Dredze

Pretrained multilingual encoders enable zero-shot cross-lingual transfer, but often produce unreliable models that exhibit high performance variance on the target language. We postulate that this high variance results fr…

Cross-Lingual TransferZero-Shot Cross-Lingual Transfer

DiTTO: A Feature Representation Imitation Approach for Improving Cross-Lingual Transfer

2023-03-04 · Shanu Kumar, Abbaraju Soujanya, Sandipan Dandapat, Sunayana Sitaram 외

Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero…

Cross-Lingual TransferZero-Shot Cross-Lingual Transfer

On Zero-shot Cross-lingual Transfer of Multilingual Neural Machine Translation

2018-10-22 · Anonymous

Transferring representations from large-scale supervised tasks to downstream tasks have shown outstanding results in Machine Learning in both Computer Vision and natural language processing (NLP). One particular example …

Cross-Lingual TransferMachine TranslationNatural Language InferenceNMT+4

Transfer Language Selection for Zero-Shot Cross-Lingual Abusive Language Detection

2022-06-02 · Juuso Eronen, Michal Ptaszynski, Fumito Masui, Masaki Arata 외

We study the selection of transfer languages for automatic abusive language detection. Instead of preparing a dataset for every language, we demonstrate the effectiveness of cross-lingual transfer learning for zero-shot …

Abusive LanguageCross-Lingual TransferTransfer Learning

mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models

2023-05-23 · Peiqin Lin, Chengzhi Hu, Zheyu Zhang, André F. T. Martins 외

Recent multilingual pretrained language models (mPLMs) have been shown to encode strong language-specific signals, which are not explicitly provided during pretraining. It remains an open question whether it is feasible …

Cross-Lingual TransferOpen-Ended Question AnsweringZero-Shot Cross-Lingual Transfer