Explore BiLSTM-CRF-Based Models for Open Relation Extraction

• URL: http://arxiv.org/abs/2104.12333v2
• Date: Tue, 9 Jul 2024 12:06:39 GMT
• Title: Explore BiLSTM-CRF-Based Models for Open Relation Extraction
• Authors: Tao Ni, Qing Wang, Gabriela Ferraro,
• Abstract summary: We develop several Open RE models based on the bidirectional LSTM-CRF (BiLSTM-CRF) neural network and different contextualized word embedding methods. We select the best combination of tagging scheme, word embedder, and BiLSTM-CRF network to achieve an Open RE model with a remarkable ability extracting on multiple-relation sentences.
• Score: 5.7380564196163855
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.