x.ent: R Package for Entities and Relations Extraction based on Unsupervised Learning and Document Structure
This work addresses relation extraction for expert end-users in domains like plant health epidemiology, though it appears incremental as it builds on existing cooccurrence and document structure methods.
The authors tackled the challenge of achieving accurate relation extraction from full text databases by proposing an approach based on cooccurrence analysis and document structure, implemented in an R package called x.ent. They demonstrated its application on two datasets, including one for plant-disease exploration in agricultural news, with an open-data platform made publicly available.
Relation extraction with accurate precision is still a challenge when processing full text databases. We propose an approach based on cooccurrence analysis in each document for which we used document organization to improve accuracy of relation extraction. This approach is implemented in a R package called \emph{x.ent}. Another facet of extraction relies on use of extracted relation into a querying system for expert end-users. Two datasets had been used. One of them gets interest from specialists of epidemiology in plant health. For this dataset usage is dedicated to plant-disease exploration through agricultural information news. An open-data platform exploits exports from \emph{x.ent} and is publicly available.