CURE: A Dataset for Clinical Understanding & Retrieval Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sheikh, Nadia Athar, Marcos, Daniel Buades, Jousse, Anne-Laure, Oladipo, Akintunde, Rousseau, Olivier, Lin, Jimmy
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915363179986944
author Sheikh, Nadia Athar
Marcos, Daniel Buades
Jousse, Anne-Laure
Oladipo, Akintunde
Rousseau, Olivier
Lin, Jimmy
author_facet Sheikh, Nadia Athar
Marcos, Daniel Buades
Jousse, Anne-Laure
Oladipo, Akintunde
Rousseau, Olivier
Lin, Jimmy
contents Given the dominance of dense retrievers that do not generalize well beyond their training dataset distributions, domain-specific test sets are essential in evaluating retrieval. There are few test datasets for retrieval systems intended for use by healthcare providers in a point-of-care setting. To fill this gap we have collaborated with medical professionals to create CURE, an ad-hoc retrieval test dataset for passage ranking with 2000 queries spanning 10 medical domains with a monolingual (English) and two cross-lingual (French/Spanish -> English) conditions. In this paper, we describe how CURE was constructed and provide baseline results to showcase its effectiveness as an evaluation tool. CURE is published with a Creative Commons Attribution Non Commercial 4.0 license and can be accessed on Hugging Face and as a retrieval task on MTEB.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06954
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CURE: A Dataset for Clinical Understanding & Retrieval Evaluation
Sheikh, Nadia Athar
Marcos, Daniel Buades
Jousse, Anne-Laure
Oladipo, Akintunde
Rousseau, Olivier
Lin, Jimmy
Information Retrieval
Given the dominance of dense retrievers that do not generalize well beyond their training dataset distributions, domain-specific test sets are essential in evaluating retrieval. There are few test datasets for retrieval systems intended for use by healthcare providers in a point-of-care setting. To fill this gap we have collaborated with medical professionals to create CURE, an ad-hoc retrieval test dataset for passage ranking with 2000 queries spanning 10 medical domains with a monolingual (English) and two cross-lingual (French/Spanish -> English) conditions. In this paper, we describe how CURE was constructed and provide baseline results to showcase its effectiveness as an evaluation tool. CURE is published with a Creative Commons Attribution Non Commercial 4.0 license and can be accessed on Hugging Face and as a retrieval task on MTEB.
title CURE: A Dataset for Clinical Understanding & Retrieval Evaluation
topic Information Retrieval
url https://arxiv.org/abs/2412.06954