id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
zkie-zero-2020		From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains	2020-05-18	12	.pdf	application/pdf	7446	833	63	From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains requires handling noisy texts, low resource settings and domain-specific KBs. Existing approaches are mostly inappropriate for this, as low-resource settings: often, no data annotated exists; coverage of open-domain knowledge bases Therefore, entity linking is frequently performed against domainspecific knowledge bases (Munnelly and Lawless, task or to train machine learning models for automatic annotation. Entity Linking describes the task of disambiguating mentions in a text against a knowledge base. been performed on entity linking against domainspecific knowledge bases. base and use full text search to retrieve candidates of the entities are in DBPedia), we manually created a domain specific knowledge base for this data We evaluate the performance of our Levenshteinbased recommender that suggests potential annotations to users (Table 3). In the future, we want to investigate more powerful recommenders, combine interactive entity linking with knowledge base completion and use online	./cache/zkie-zero-2020.pdf	./txt/zkie-zero-2020.txt