Сравнение на методи

	Многоезикова невронна мрежа за графи (Multilingual Graph Neural Network)	Многоезикови векторни представяния на изречения
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2019	2019–2022
Създател	Various (Kipf & Welling 2017 for GNN; multilingual extensions from NLP community ~2019)	Reimers, N. & Gurevych, I.; Feng, F. et al. (Google)
Тип	Graph-based deep learning with multilingual node/edge features	Cross-lingual representation learning
Основополагащ източник	Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR 2017.	Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525.
Други названия	Multilingual GNN, cross-lingual GNN, multilingual graph network, multilingual relational GNN	multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings
Свързани	5	5
Резюме	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.	Multilingual sentence embeddings map sentences from many languages into a single shared vector space so that semantically equivalent sentences — regardless of language — land close together. Models such as LaBSE, multilingual Sentence-BERT, and mUSE have made it practical to compare, retrieve, and classify text across 50 to 100+ languages without translating anything first.