论文标题
Multi $^2 $ OIE：基于多头注意的多语言开放信息提取伯特
Multi$^2$OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT
论文作者
论文摘要
在本文中，我们提出了Multi $^2 $ OIE，该论文通过将BERT与多头注意力结合使用，可以执行开放信息提取（开放IE）。我们的模型是具有有效有效的参数提取方法的序列标记系统。我们使用受多模式变压器启发的查询，钥匙和值设置，以多头注意力替换先前使用的双向长期记忆体系结构。在两个基准评估数据集（Re-OIE2016和Carb）上，Multi $^2 $ OIE优于现有的序列标记系统，具有高计算效率。此外，我们将提出的方法应用于使用多语言BERT的多语言打开IE。针对两种语言（西班牙语和葡萄牙语）引入的新基准数据集的实验结果表明，我们的模型在没有培训目标语言的情况下优于其他多语言系统。
In this paper, we propose Multi$^2$OIE, which performs open information extraction (open IE) by combining BERT with multi-head attention. Our model is a sequence-labeling system with an efficient and effective argument extraction method. We use a query, key, and value setting inspired by the Multimodal Transformer to replace the previously used bidirectional long short-term memory architecture with multi-head attention. Multi$^2$OIE outperforms existing sequence-labeling systems with high computational efficiency on two benchmark evaluation datasets, Re-OIE2016 and CaRB. Additionally, we apply the proposed method to multilingual open IE using multilingual BERT. Experimental results on new benchmark datasets introduced for two languages (Spanish and Portuguese) demonstrate that our model outperforms other multilingual systems without training data for the target languages.
