Pre-trained Text-to-Text Language Models (LMs), such as T5 or BART yield promising results in the Knowledge Graph Question Answering (KGQA) task. However, the capacity of the models is limited and the quality decreases for questions with less popular entities. In this paper, we present a novel approach which works on top of the pre-trained Text-to-Text QA system to address this issue. Our simple yet effective method performs filtering and re-ranking of generated candidates based on their types derived from Wikidata "instance_of" property.

翻译：预训练的文本到文本语言模型（如T5或BART）在知识图谱问答（KGQA）任务中展现出令人瞩目的成果。然而，这些模型的能力存在局限，对于涉及较少流行实体的提问，其回答质量会下降。本文提出了一种新颖方法，该方法基于预训练的文本到文本问答系统之上，旨在解决上述问题。我们这一简单而有效的方法，依据源自Wikidata中“instance_of”属性推导出的候选答案类型，对生成的答案候选进行过滤和重新排序。