x.ent: R Package for Entities and Relations Extraction based on Unsupervised Learning and Document Structure

TL;DR

This paper introduces x.ent, an R package that improves relation extraction accuracy in full-text documents by leveraging document structure and co-occurrence analysis, aiding expert querying in specialized domains.

Contribution

The paper presents a novel unsupervised relation extraction method based on document organization, implemented in an accessible R package for domain-specific information retrieval.

Findings

Improved relation extraction accuracy using document structure.

Application to epidemiology and plant health datasets.

Publicly available platform for agricultural information exploration.

Abstract

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.