CogIE: An Information Extraction Toolkit for Bridging Texts and CogNet

Abstract

CogNet is a knowledge base that integrates three types of knowledge: linguistic knowledge, world knowledge and commonsense knowledge. In this paper, we propose an information extraction toolkit, called CogIE, which is a bridge connecting raw texts and CogNet. CogIE has three features: versatile, knowledge-grounded and extensible. First, CogIE is a versatile toolkit with a rich set of functional modules, including named entity recognition, entity typing, entity linking, relation extraction, event extraction and framesemantic parsing. Second, as a knowledgegrounded toolkit, CogIE can ground the extracted facts to CogNet and leverage different types of knowledge to enrich extracted results. Third, for extensibility, owing to the design of three-tier architecture, CogIE is not only a plug-and-play toolkit for developers but also an extensible programming framework for researchers. We release an open-access online system 1 to visually extract information from texts. Source code, datasets and pre-trained models are publicly available at GitHub 2 , with a short instruction video 3 .

DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population

“…To date, a few remarkable open-source and longterm maintained information extraction toolkits have been developed, such as Spacy (Vasiliev, 2020) for named entity recognition (NER), TagMe (Ferragina and Scaiella, 2010) for entity linking (EL), OpenNRE (Han et al, 2019) for relation extraction, Stanford OpenIE (Martínez-Rodríguez et al, 2018) for open information extraction, RESIN for event extraction (Wen et al, 2021) and so on Jin et al, 2021). However, there are still several non-trivial issues that hinder the applicability for real-world applications.…”