Dataset Card for Explain Artworks: ExpArt

This dataset card aims to be a base template for new datasets. It has been generated using this raw template.

Dataset Card for "Wiki-ImageReview1.0"

Dataset Summary

Explain Artworks: ExpArt is designed to enhance the capabilities of large-scale vision-language models (LVLMs) in analyzing and describing artworks. Drawing from a comprehensive array of English Wikipedia art articles, the dataset encourages LVLMs to create in-depth descriptions based on images with or without accompanying titles. This endeavor aims to improve LVLMs' proficiency in discerning and articulating the historical and thematic nuances of art. Explain Artworks: ExpArt not only aims to elevate AI's understanding and critique of art but also seeks to forge a stronger connection between artificial intelligence and art history. With approximately 10,000 articles, the dataset introduces specialized metrics for assessing the effectiveness of LVLMs in art explanation, focusing on their interpretation of visual and textual cues.

Supported Tasks and Leaderboards

[More Information Needed]

Languages

This dataset is available in English.

Dataset Structure

The following examples illustrate two different formats of the training dataset. The first includes a ‘title‘ field, while the second does not．

Dataset Example (with Title)

{
  "id": "0001_T",
  "title": "Mona Lisa",
  "conversations": [
    {
      "from": "user",
      "value": "<img>/images/Mona Lisa.jpg</img>\nFocus on Mona Lisa and explore the history."
    },
    {
      "from": "assistant",
      "value": "Of Leonardo da Vinci’s works, the Mona Lisa is the only portrait whose authenticity...."
    }
  ]
}

Dataset Example (without Title)

{
  "id": "0001_NT",
  "conversations": [
    {
      "from": "user",
      "value": "<img>/images/Mona Lisa.jpg</img>\nFocus on this artwork and explore the history."
    },
    {
      "from": "assistant",
      "value": "Of Leonardo da Vinci’s works, the Mona Lisa is the only portrait whose authenticity...."
    }
  ]
}

Data Instances

English Example

from datasets import load_dataset

dataset = load_dataset("naist-nlp/ExpArt")

print(dataset)
# DatasetDict({
#     train: Dataset({
#         features: ['id', 'title', 'conversations'],
#         num_rows: X  # Replace X with the actual number of rows in your dataset
#     })
# })

# Example of accessing a single data instance
example = dataset['train'][0]
print(example)
# {
#   "id": "0001_T",
#   "title": "Mona Lisa",
#   "conversations": [
#     {
#       "from": "user",
#       "value": "<img src='/images/Mona%20Lisa.jpg'></img>\nFocus on Mona Lisa and explore the history."
#     },
#     {
#       "from": "assistant",
#       "value": "Of Leonardo da Vinci’s works, the Mona Lisa is the only portrait whose authenticity...."
#     }
#   ]
# }