Explore BiLSTM-CRF-Based Models for Open Relation Extraction
This work addresses the problem of overlapping relations in text for natural language processing applications, but it appears incremental as it builds on existing BiLSTM-CRF methods.
The paper tackled the challenge of extracting multiple relations from text sentences in Open Relation Extraction by developing models based on BiLSTM-CRF networks and contextualized word embeddings, achieving a model with remarkable extracting ability on multiple-relation sentences.
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.