Difference between revisions of "Family Matters: Company Relations Extraction from Wikipedia"
(Family Matters: Company Relations Extraction from Wikipedia - basic info) |
(Wikilinks) |
||
| Line 1: | Line 1: | ||
| − | '''Family Matters: Company Relations Extraction from Wikipedia''' - scientific work related to Wikipedia quality published in 2016, written by Artem Kuznetsov, Pavel Braslavski and Vladimir Ivanov. | + | '''Family Matters: Company Relations Extraction from Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2016, written by [[Artem Kuznetsov]], [[Pavel Braslavski]] and [[Vladimir Ivanov]]. |
== Overview == | == Overview == | ||
| − | The study described in the paper deals with the extraction of relations between organizations from the Russian Wikipedia. Authors experiment with two data sources for supervised methods – manual annotations made from scratch and relations from infoboxes with subsequent sentence matching, as well as different feature sets and learning methods – SVM, CRF, and UIMA Ruta. Results show that the automatically obtained training data delivers worse results than manually annotated data, but the former approach is promising due to its scalability. Evaluation of relations extracted from a subset of Wikipedia pages that are mapped to the Russian state company registry proves that external sources can enrich and complement official databases. | + | The study described in the paper deals with the extraction of relations between organizations from the Russian [[Wikipedia]]. Authors experiment with two data sources for supervised methods – manual annotations made from scratch and relations from [[infoboxes]] with subsequent sentence matching, as well as different feature sets and learning methods – SVM, CRF, and UIMA Ruta. Results show that the automatically obtained training data delivers worse results than manually annotated data, but the former approach is promising due to its scalability. Evaluation of relations extracted from a subset of Wikipedia pages that are mapped to the Russian state company registry proves that external sources can enrich and complement official databases. |
Revision as of 21:29, 20 June 2019
Family Matters: Company Relations Extraction from Wikipedia - scientific work related to Wikipedia quality published in 2016, written by Artem Kuznetsov, Pavel Braslavski and Vladimir Ivanov.
Overview
The study described in the paper deals with the extraction of relations between organizations from the Russian Wikipedia. Authors experiment with two data sources for supervised methods – manual annotations made from scratch and relations from infoboxes with subsequent sentence matching, as well as different feature sets and learning methods – SVM, CRF, and UIMA Ruta. Results show that the automatically obtained training data delivers worse results than manually annotated data, but the former approach is promising due to its scalability. Evaluation of relations extracted from a subset of Wikipedia pages that are mapped to the Russian state company registry proves that external sources can enrich and complement official databases.
