Extracting multiple relations from text sentences is still a challenge for current Open Relation Extraction (Open RE) tasks. In this paper, we develop several Open RE models based on the bidirectional LSTM-CRF (BiLSTM-CRF) neural network and different contextualized word embedding methods. We also propose a new tagging scheme to solve overlapping problems and enhance models' performance. From the evaluation results and comparisons between models, we select the best combination of tagging scheme, word embedder, and BiLSTM-CRF network to achieve an Open RE model with a remarkable extracting ability on multiple-relation sentences.

翻译：从文本句中提取多个关系仍然是当前开放关系提取(开放 RE) 任务的挑战。 在本文中, 我们根据双向 LSTM- CRF (BILSTM- CRF) 神经网络和不同背景化的词嵌入方法, 开发了多个开放 RE 模型。 我们还提出了一个新的标记方案, 以解决重叠问题, 提高模型的性能 。 通过评估结果和模型之间的比较, 我们选择了标记方案、 字嵌入器 和 BILSTM- CRF 网络 的最佳组合, 以实现在多重关系判决上具有显著提取能力的开放 RE 模型 。