Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
This work addresses information extraction for scientific knowledge graph construction, offering a domain-agnostic approach that is incremental in combining existing tasks.
The paper tackles the problem of extracting entities, relations, and coreference from scientific articles by introducing a multi-task framework called SciIE, which outperforms previous models without domain-specific features.
We introduce a multi-task setup of identifying and classifying 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 Scientific Information Extractor (SciIE) for 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.