Explore BiLSTM-CRF-Based Models for Open Relation Extraction
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 11 of its 30 references that are in the map. First posted on arXiv 26 Apr 2021.
Builds on
11 of 30 references.
References · 11
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2018Deep contextualized word representationscited by 2,290
- 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 546
- 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
- 2017Learned in Translation: Contextualized Word Vectorscited by 104
- 2017Joint Extraction of Entities and Relations Based on a Novel Tagging Schemecited by 102
- 2018Neural Open Information Extractioncited by 50
- 2019Hybrid Neural Tagging Model for Open Relation Extractioncited by 5
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 1.
2 papers.