arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.13952cs.CLcs.AIcs.IR
收藏

KnowGL:文本知识生成与链接

KnowGL: Knowledge Generation and Linking from Text

IBM Research AI(IBM研究院人工智能部门);Thomas J. Watson Research Center(托马斯·J·沃森研究中心)

Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Nandana Mihindukulasooriya, Owen Cornec, Alfio Massimiliano Gliozzo

摘要:

我们提出了KnowGL,一个工具,允许将文本转换为结构化的关系数据表示为一组ABox断言符合TBox的一个给定的知识图谱(KG),如Wikidata。我们利用预先训练的序列到序列语言模型,例如BART,将这个问题作为序列生成任务来解决。给定一个句子,我们微调这些模型来检测实体提及对,并联合生成一组由KG的完整语义注释组成的事实,例如实体标签,实体类型及其关系。为了展示我们的工具的功能,我们构建了一个Web应用程序,该应用程序由一组UI小部件组成,这些UI小部件可以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://huggingface.co/ibm/knowgl-large上提供KnowGL模型。

英文摘要:

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.

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。

↑