Extracting multiple relations from text sentences is still a challenge for Open Relation Extraction tasks . In this paper, we develop several Open RE models based on the bidirectional LSTM-CRF neuralnetwork and different contextualized word embedding methods . We also propose anew tagging scheme to solve overlapping problems and enhance models’performance . From the evaluation results and comparisons between models, weselect the best combination of tagging scheme, word embedder, and BiLSTM

Author(s) : Tao Ni, Qing Wang, Gabriela Ferraro

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : models - open - word - scheme - crf -

Leave a Reply

Your email address will not be published. Required fields are marked *