We propose KnowGL, a tool that allows converting text into structured relational data represented as a set of ABox assertions compliant with the TBox of a given Knowledge Graph (KG), such as Wikidata. We address this problem as a sequence generation task by leveraging pre-trained sequence-to-sequence language models, e.g. BART. Given a sentence, we fine-tune such models to detect pairs of entity mentions and jointly generate a set of facts consisting of the full set of semantic annotations for a KG, such as entity labels, entity types, and their relationships. To showcase the capabilities of our tool, we build a web application consisting of a set of UI widgets that help users to navigate through the semantic data extracted from a given input text. We make the KnowGL model available at https://huggingface.co/ibm/knowgl-large.
翻译:我们建议KnowGL, 这是一种工具,可以将文字转换成结构化的关系数据, 以符合特定知识图(KG)的TBox 的一组 ABox 数据为代表, 如 Wikigata 。 我们通过使用事先训练的序列至序列语言模型, 如 BART, 将这个问题作为一个序列生成任务来解决。 我们用一个句子, 微调这些模型来检测一对实体提到的情况, 并联合生成一套事实, 包括一套完整的KG 语义说明, 如实体标签、 实体类型及其关系。 为了展示我们工具的能力, 我们建立一个由一组 UI 部件组成的网络应用程序, 帮助用户浏览从给定输入文本中提取的语义数据 。 我们在 https:// ugingface. co/ibm/ louggl-master 上提供 KnowGL 模型 。