Abstract
The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples. In this demonstration we introduce a new workflow where the analyst directly verbalizes the entities/relations, which are then used by a Textual Entailment model to perform zero-shot IE. We present the design and implementation of a toolkit with a user interface, as well as experiments on four IE tasks that show that the system achieves very good performance at zero-shot learning using only 5-15 minutes per type of a user's effort. Our demonstration system is open-sourced at https://github.com/BBN-E/ZS4IE. A demonstration video is available at https://vimeo.com/676138340.
Cite
CITATION STYLE
Sainz, O., Qiu, H., de Lacalle, O. L., Agirre, E., & Min, B. (2022). ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations. In NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session (pp. 27–38). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.naacl-demo.4
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
