Salvato in:
Dettagli Bibliografici
Autori principali: Gomes, Luís, Branco, António, Silva, João, Rodrigues, João, Santos, Rodrigo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2407.19527
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929439681544192
author Gomes, Luís
Branco, António
Silva, João
Rodrigues, João
Santos, Rodrigo
author_facet Gomes, Luís
Branco, António
Silva, João
Rodrigues, João
Santos, Rodrigo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19527
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family
Gomes, Luís
Branco, António
Silva, João
Rodrigues, João
Santos, Rodrigo
Computation and Language
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.
title Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family
topic Computation and Language
url https://arxiv.org/abs/2407.19527