Beyond One-Size-Fits-All: Multi-Domain, Multi-Task Framework for Embedding Model Selection

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Khetan, Vivek
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916375141810176
author Khetan, Vivek
author_facet Khetan, Vivek
contents This position paper proposes a systematic approach towards developing a framework to help select the most effective embedding models for natural language processing (NLP) tasks, addressing the challenge posed by the proliferation of both proprietary and open-source encoder models.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00458
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond One-Size-Fits-All: Multi-Domain, Multi-Task Framework for Embedding Model Selection
Khetan, Vivek
Computation and Language
Information Retrieval
This position paper proposes a systematic approach towards developing a framework to help select the most effective embedding models for natural language processing (NLP) tasks, addressing the challenge posed by the proliferation of both proprietary and open-source encoder models.
title Beyond One-Size-Fits-All: Multi-Domain, Multi-Task Framework for Embedding Model Selection
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2404.00458