introvoyz041/ChEBI-20-MM

ChEBI-20-MM是基于ChEBI-20数据集扩展的多模态基准数据集，旨在为分子科学领域的模型评估提供全面的基准。该数据集整合了多种分子数据模态，包括InChI、IUPAC、SELFIES和图像，使其成为适用于多种分子任务的多功能工具。数据集特别关注以下关键领域：分子生成（评估模型生成准确分子结构的能力）、图像识别（测试模型将分子图像转换为其他表示格式的熟练程度）、IUPAC识别（评估模型从其他表示格式生成IUPAC名称的能力）、分子标注（评估模型为分子结构生成描述性标注的能力）以及检索任务（测量模型准确高效检索分子信息的能力）。

The ChEBI-20-MM is an extensive and multi-modal benchmark developed from the ChEBI-20 dataset. It is designed to provide a comprehensive benchmark for evaluating various models capabilities in the field of molecular science. This benchmark integrates multi-modal data, including InChI, IUPAC, SELFIES, and images, making it a versatile tool for a wide range of molecular tasks. The benchmark is tailored to assess models in several key areas: Molecule Generation (evaluating the ability of models to generate accurate molecular structures), Image Recognition (testing models on their proficiency in converting molecular images into other representational formats), IUPAC Recognition (evaluating the ability of models to generate IUPAC names from other representational formats), Molecular Captioning (assessing the capability of models to generate descriptive captions for molecular structures), and Retrieval Tasks (measuring the effectiveness of models in retrieving molecular information accurately and efficiently).