| Título |
A simple hybrid approach to recognizing textual entailment
|
| Tipo |
Revista |
| Sub-tipo |
JCR |
| Descripción |
Journal of Intelligent & Fuzzy Systems |
| Resumen |
We explore various machine learning-based classifiers applied to rule-based features for recognizing textual entailment.Thefeatures,extractedwithasetofsynthesizedmatchingrules,reflectsyntacticandsemanticsimilaritybetween the text and the hypothesis. The fact that we use only seven relatively simple features makes our method suitable for low-resource languages. We test our method on the test sets of the RTE competitions and achieve accuracy of up to 69.13%.
|
| Observaciones |
DOI:10.3233/JIFS-169474, JCR impact factor 2016: 1.261 (Q3)
|
| Lugar |
Amsterdam |
| País |
Paises Bajos |
| No. de páginas |
2873-2885 |
| Vol. / Cap. |
v. 34 no. 5 |
| Inicio |
2018-11-01 |
| Fin |
|
| ISBN/ISSN |
|
