TREC-AToMiC/atomic2023-small_text2image

---
language:
- en
task_categories:
- multimodal-retrieval
source_datasets:
- atomic
task_ids:
- text-to-image
config_names:
- corpus
tags:
- multimodal-retrieval
dataset_info:
- config_name: default
features:
- name: query-id
dtype: string
- name: corpus-id
dtype: string
- name: score
dtype: int8
- name: annotator
dtype: string
splits:
- name: qrels
num_examples: 24728
- config_name: corpus
features:
- name: id
dtype: string
- name: url
dtype: string
- name: ref
dtype: string
- name: att
dtype: string
- name: alt
dtype: string
- name: path
dtype: string
splits:
- name: corpus
num_examples: 23400
- config_name: query
features:
- name: id
dtype: string
- name: page_title
dtype: string
- name: section_title
dtype: string
- name: hierachy
dtype: string
- name: context_page_description
dtype: string
- name: context_section_description
dtype: string
splits:
- name: query
num_examples: 74
configs:
- config_name: default
data_files:
- split: qrels
path: qrels.jsonl
- config_name: corpus
data_files:
- split: corpus
path: corpus.jsonl
- config_name: query
data_files:
- split: query
path: query.jsonl
---

原始信息汇总

数据集概述

基本信息

• 语言: 英语
• 任务类别: 多模态检索
• 源数据集: Atomic
• 任务ID: 文本到图像
• 配置名称: corpus
• 标签: 多模态检索

数据集配置

默认配置

• 特征:
  • query-id: 字符串
  • corpus-id: 字符串
  • score: 字节
  • annotator: 字符串
• 分割:
  • qrels: 24728个示例

语料库配置

• 特征:
  • id: 字符串
  • url: 字符串
  • ref: 字符串
  • att: 字符串
  • alt: 字符串
  • path: 字符串
• 分割:
  • corpus: 23400个示例

查询配置

• 特征:
  • id: 字符串
  • page_title: 字符串
  • section_title: 字符串
  • hierachy: 字符串
  • context_page_description: 字符串
  • context_section_description: 字符串
• 分割:
  • query: 74个示例

数据文件

• 默认配置:
  • qrels: qrels.jsonl
• 语料库配置:
  • corpus: corpus.jsonl
• 查询配置:
  • query: query.jsonl