Are All Languages Created Equal in Multilingual BERT?
Multilingual BERT (mBERT) trained on 104 languages has shown surprisingly good cross-lingual performance on several NLP tasks, even without explicit cross-lingual signals. However, these evaluations have focused on cross-lingual transfer with high-resource languages, covering only a third of the languages covered by mBERT. We explore how mBERT performs on a much wider set of languages, focusing on the quality of representation for low-resource languages, measured by within-language performance. We consider three tasks: Named Entity Recognition (99 languages), Part-of-speech Tagging, and Dependency Parsing (54 languages each). mBERT does better than or comparable to baselines on high resource languages but does much worse for low resource languages. Furthermore, monolingual BERT models for these languages do even worse. Paired with similar languages, the performance gap between monolingual BERT and mBERT can be narrowed. We find that better models for low resource languages require more efficient pretraining techniques or more data.
Code (1)
Tasks
AllCross-Lingual TransferDependency Parsingnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Part-Of-Speech TaggingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Are Pretrained Multilingual Models Equally Fair Across Languages?
Pretrained multilingual language models can help bridge the digital language divide, enabling high-quality NLP models for lower resourced languages. Studies of multilingual models have so far focused on performance, cons…
Cloze TestFairnessPretrained Multilingual Language ModelsXLM-RAre Pretrained Multilingual Models Equally Fair Across Languages?
Pretrained multilingual language models can help bridge the digital language divide, enabling high-quality NLP models for lower-resourced languages. Studies of multilingual models have so far focused on performance, cons…
Cloze TestFairnessPretrained Multilingual Language ModelsXLM-RMultilingual is not enough: BERT for Finnish
Deep learning-based language models pretrained on large unannotated text corpora have been demonstrated to allow efficient transfer learning for natural language processing, with recent approaches such as the transformer…
Dependency Parsingnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2Training dataset and dictionary sizes matter in BERT models: the case of Baltic languages
Large pretrained masked language models have become state-of-the-art solutions for many NLP problems. While studies have shown that monolingual models produce better results than multilingual models, the training dataset…
Dependency Parsingnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1Factual Consistency of Multilingual Pretrained Language Models
Pretrained language models can be queried for factual knowledge, with potential applications in knowledge base acquisition and tasks that require inference. However, for that, we need to know how reliable this knowledge …
XLM-R