ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations

Autor:	Sainz, Oscar, Qiu, Haoling, de Lacalle, Oier Lopez, Agirre, Eneko, Min, Bonan
Rok vydání:	2022
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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 . Comment: Accepted at NAACL2022 Demo track
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2203.13602 Zobrazit plný text záznamu View this record from Arxiv