Сравнение методов

	Многоязычная графовая нейронная сеть	Мультиязычный трансформер
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2019	2019–2020
Автор метода	Various (Kipf & Welling 2017 for GNN; multilingual extensions from NLP community ~2019)	Devlin et al. (mBERT); Conneau et al. (XLM-R)
Тип	Graph-based deep learning with multilingual node/edge features	Pre-trained cross-lingual language model
Основополагающий источник	Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR 2017.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, pp. 4171–4186. Association for Computational Linguistics.
Другие названия	Multilingual GNN, cross-lingual GNN, multilingual graph network, multilingual relational GNN	multilingual LM, cross-lingual transformer, mBERT-style model, multilingual pre-trained model
Связанные	5	4
Сводка	A Multilingual Graph Neural Network (Multilingual GNN) applies graph-based message-passing over nodes and edges that carry features from two or more languages. It is used for tasks such as cross-lingual entity alignment, multilingual knowledge-graph completion, and relation extraction across parallel or comparable corpora, allowing structural and semantic information from multiple languages to be jointly learned.	A multilingual transformer is a pre-trained language model built on the transformer architecture and trained jointly on text from dozens to over one hundred languages. Models such as mBERT and XLM-RoBERTa learn shared cross-lingual representations, enabling zero-shot or few-shot transfer: a model fine-tuned on English data can often be applied directly to French, German, Arabic, or Chinese without language-specific labels.