Paper introduces SEA-Embedding, open text embeddings for Southeast Asia

Arxiv CS.CL (NLP/language models)

SEA-Embedding provides open and reproducible text embedding models for Southeast Asian languages, addressing the lack of open models in the region. The paper focuses on reproducibility by using open training data and methods.

embeddings

Arxiv CS.CL (NLP/language models)·Peerat LimkonchotiwatRaymond NgSarana NutanongJian Gang Ngui

8 days ago