Machine learningDeep learning / NLP / CV

Multilingual Sentence Embeddings

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.

MethodMind'de açSoonVideoSoon

Tam yöntemi oku

Members only

Sources

Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525. link ↗
Feng, F., Yang, Y., Cer, D., Arivazhagan, N. & Wang, W. (2022). Language-agnostic BERT Sentence Embedding. Proceedings of ACL 2022, 878–891. DOI: 10.18653/v1/2022.acl-long.62 ↗

Referenced by

Domain-adaptive sentence embeddings Multilingual Diffusion Model Multilingual Doc2Vec Multilingual GAN Multilingual graph neural network Multilingual Image Classification Multilingual LSTM Multilingual Multilayer Perceptron Multilingual question answering Multilingual Reinforcement Learning Multilingual RoBERTa-based Classification Multilingual Sentiment Analysis Multilingual topic modeling Multilingual Transformer Multilingual variational autoencoder Multilingual vision transformer

Bu sayfada bir hata mı var? Bildir / düzeltme öner →

Tam yöntemi oku

Sources

Related methods

Referenced by