Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family
This provides accessible, high-performance sentence embeddings for Portuguese speakers and researchers, though it is incremental as it adapts existing methods to a new language.
The authors tackled the lack of open-source sentence encoders for Portuguese by developing the Serafim PT* family, which achieves state-of-the-art performance across various model sizes and is made available under a permissive license.
Sentence encoder encode the semantics of their input, enabling key downstream applications such as classification, clustering, or retrieval. In this paper, we present Serafim PT*, a family of open-source sentence encoders for Portuguese with various sizes, suited to different hardware/compute budgets. Each model exhibits state-of-the-art performance and is made openly available under a permissive license, allowing its use for both commercial and research purposes. Besides the sentence encoders, this paper contributes a systematic study and lessons learned concerning the selection criteria of learning objectives and parameters that support top-performing encoders.