Multi$^2$OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT
This work addresses open IE for multilingual text processing, offering incremental improvements in efficiency and performance over prior methods.
The paper tackles open information extraction by proposing Multi^2OIE, a sequence-labeling system combining BERT with multi-head attention, which outperforms existing systems on benchmarks like Re-OIE2016 and CaRB and shows effectiveness in multilingual settings without target language training data.
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.