arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.01763cs.CLcs.AI
收藏

Seq2RDF:一个从自然语言文本派生三元组的端到端应用程序

Seq2RDF: An end-to-end application for deriving Triples from Natural Language Text

Rensselaer Polytechnic Institute(伦斯勒理工学院)

Yue Liu, Tongtao Zhang, Zhicheng Liang, Heng Ji, Deborah L. McGuinness

摘要:

我们提出了一个端到端的方法,采取非结构化的文本输入,并生成符合给定的词汇表的结构化输出。受神经机器翻译最近成功的启发,我们将给定知识图中的三元组视为独立的图形语言,并提出了一个编码器-解码器框架,该框架具有利用知识图谱嵌入的注意力机制。我们的模型使用选定的知识图谱词汇学习从自然语言文本到主语-谓语-宾语形式的三重表示的映射。三个不同的数据集上的实验表明,我们实现了竞争力的F1-措施的基线使用我们简单而有效的方法。演示视频包括在内。

英文摘要:

We present an end-to-end approach that takes unstructured textual input and generates structured output compliant with a given vocabulary. Inspired by recent successes in neural machine translation, we treat the triples within a given knowledge graph as an independent graph language and propose an encoder-decoder framework with an attention mechanism that leverages knowledge graph embeddings. Our model learns the mapping from natural language text to triple representation in the form of subject-predicate-object using the selected knowledge graph vocabulary. Experiments on three different data sets show that we achieve competitive F1-Measures over the baselines using our simple yet effective approach. A demo video is included.

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。

↑