Evaluation of Open Information Extraction Methods Using Reuters-21578 Database
| Title | Evaluation of Open Information Extraction Methods Using Reuters-21578 Database |
| Publication Type | Conference Paper |
| Year of Publication | 2018 |
| Authors | Rodríguez, Juan M., Merlino, Hernán D., Pesado, Patricia, García-Martínez, Ramón |
| Conference Name | Proceedings of the 2Nd International Conference on Machine Learning and Soft Computing |
| Date Published | February 2018 |
| Publisher | ACM |
| Conference Location | New York, NY, USA |
| ISBN Number | 978-1-4503-6336-5 |
| Keywords | Air gaps, clausIE, composability, Human Behavior, Knowledge extraction, Metrics, natural language processing, OIE, OLLIE, open information extraction, pubcrawl, resilience, Resiliency, reverb, self-supervised extraction, semantic relation extraction |
| Abstract | The following article shows the precision, the recall and the F1-measure for three knowledge extraction methods under Open Information Extraction paradigm. These methods are: ReVerb, OLLIE and ClausIE. For the calculation of these three measures, a representative sample of Reuters-21578 was used; 103 newswire texts were taken randomly from that database. A big discrepancy was observed, after analyzing the obtained results, between the expected and the observed precision for ClausIE. In order to save the observed gap in ClausIE precision, a simple improvement is proposed for the method. Although the correction improved the precision of Clausie, ReVerb turned out to be the most precise method; however ClausIE is the one with the better F1-measure. |
| URL | https://dl.acm.org/doi/10.1145/3184066.3184099 |
| DOI | 10.1145/3184066.3184099 |
| Citation Key | rodriguezEvaluationOpenInformation2018 |