ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations
Oscar Sainz, Haoling Qiu, Oier Lopez de Lacalle, Eneko Agirre, Bonan Min
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.
BibTeX
@inproceedings{sainz-etal-2022-zs4ie,
title = "{ZS}4{IE}: A toolkit for Zero-Shot Information Extraction with simple Verbalizations",
author = "Sainz, Oscar and
Qiu, Haoling and
Lopez de Lacalle, Oier and
Agirre, Eneko and
Min, Bonan",
editor = "Hajishirzi, Hannaneh and
Ning, Qiang and
Sil, Avi",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-demo.4/",
doi = "10.18653/v1/2022.naacl-demo.4",
pages = "27--38"
}