面向知识图谱问答的基于实体预训练GPT的SPARQL生成
SPARQL Generation with Entity Pre-trained GPT for KG Question Answering
AI总结：
该研究面向知识图谱问答任务，以实体链接正确为前提，提出基于CWA下所有实体预训练GPT模型以生成SPARQL查询，找出了少/零样本下的难点，在3-shots测试中获62.703%的精确匹配准确率。
摘要：
近年来，知识图谱（Knowledge Graphs）的普及度迅速提升。所有这些知识都可供人们通过互联网上的众多在线数据库进行查询。不过，若非编程用户能够获取他们想要了解的任何信息，将是一项重大成就。目前已有大量研究致力于利用自然语言处理工具解决这一任务，诸多挑战赛也推动了相关创新。我们的方法以自然语言问题上的实体链接正确为前提，训练GPT模型从这些问题生成SPARQL查询。我们成功找出了该任务在少样本或零样本场景下最难解决的属性，并提出基于所有实体（在封闭世界假设CWA下）进行预训练以提升性能。我们在3次样本（3-shots）测试中取得了62.703%的SPARQL精确匹配准确率，在实体链接挑战赛上的F1值为0.809，在问答挑战赛上的F1值为0.009。
英文摘要：
Knowledge Graphs popularity has been rapidly growing in last years. All that knowledge is available for people to query it through the many online databases on the internet. Though, it would be a great achievement if non-programmer users could access whatever information they want to know. There has been a lot of effort oriented to solve this task using natural language processing tools and creativity encouragement by way of many challenges. Our approach focuses on assuming a correct entity linking on the natural language questions and training a GPT model to create SPARQL queries from them. We managed to isolate which property of the task can be the most difficult to solve at few or zero-shot and we proposed pre-training on all entities (under CWA) to improve the performance. We obtained a 62.703% accuracy of exact SPARQL matches on testing at 3-shots, a F1 of 0.809 on the entity linking challenge and a F1 of 0.009 on the question answering challenge.
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。
