Abstract
We introduce a multi-task setup of identifying entities, relations, and coreference clusters in scientific articles. We create SciERC, a dataset that includes annotations for all three tasks and develop a unified framework called SciIE with shared span representations. The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links. Experiments show that our multi-task model outperforms previous models in scientific information extraction without using any domain-specific features. We further show that the framework supports construction of a scientific knowledge graph, which we use to analyze information in scientific literature.- Anthology ID:
- D18-1360
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3219–3232
- Language:
- URL:
- https://aclanthology.org/D18-1360
- DOI:
- 10.18653/v1/D18-1360
- Cite (ACL):
- Yi Luan, Luheng He, Mari Ostendorf, and Hannaneh Hajishirzi. 2018. Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3219–3232, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction (Luan et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/D18-1360.pdf
- Code
- additional community code
- Data
- SciERC, SemEval-2017 Task-10, Semantic Scholar