Multi$^2$OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT

17 Sep 2020  ·  Youngbin Ro, Yukyung Lee, Pilsung Kang ·

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.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Open Information Extraction CaRB Multi2OIE F1 52.3 # 7

Methods