TransGPT：面向交通的多模态生成式预训练Transformer
TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation
AI总结：
提出面向交通领域的多模态大语言模型TransGPT，包含单模态变体TransGPT-SM和多模态变体TransGPT-MM，在多个交通任务基准上优于基线模型，并展示其在交通分析与建模中的广泛应用潜力。
摘要：
自然语言处理（NLP）是智能交通系统（ITS）的关键组成部分，但在交通领域面临诸多挑战，如领域特定知识与数据，以及多模态输入输出。本文提出TransGPT，一种面向交通领域的新型（多模态）大语言模型，包含两个独立变体：处理单模态数据的TransGPT-SM和处理多模态数据的TransGPT-MM。TransGPT-SM在单模态交通数据集（STD）上微调，该数据集包含交通领域各种来源的文本数据。TransGPT-MM在多模态交通数据集（MTD）上微调，该数据集由我们手动从交通领域的三个领域收集：驾驶考试、交通标志和地标。我们在交通领域不同任务的多个基准数据集上评估TransGPT，并表明它在大多数任务上优于基线模型。我们还展示了TransGPT在交通分析和建模方面的潜在应用，如生成合成交通场景、解释交通现象、回答交通相关问题、提供交通建议和生成交通报告。这项工作推进了交通领域NLP的最新技术，并为ITS研究人员和从业者提供了有用的工具。
英文摘要：
Natural language processing (NLP) is a key component of intelligent transportation systems (ITS), but it faces many challenges in the transportation domain, such as domain-specific knowledge and data, and multi-modal inputs and outputs. This paper presents TransGPT, a novel (multi-modal) large language model for the transportation domain, which consists of two independent variants: TransGPT-SM for single-modal data and TransGPT-MM for multi-modal data. TransGPT-SM is finetuned on a single-modal Transportation dataset (STD) that contains textual data from various sources in the transportation domain. TransGPT-MM is finetuned on a multi-modal Transportation dataset (MTD) that we manually collected from three areas of the transportation domain: driving tests, traffic signs, and landmarks. We evaluate TransGPT on several benchmark datasets for different tasks in the transportation domain, and show that it outperforms baseline models on most tasks. We also showcase the potential applications of TransGPT for traffic analysis and modeling, such as generating synthetic traffic scenarios, explaining traffic phenomena, answering traffic-related questions, providing traffic recommendations, and generating traffic reports. This work advances the state-of-the-art of NLP in the transportation domain and provides a useful tool for ITS researchers and practitioners.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
