Also categorized in Entailment:
Detecting Expected Answer Relations through Textual Entailment
x hide permanently

Refining the Judgment Threshold to Improve Recognizing Textual Entailment Using Similarity

Home - Springer
In recent years, Recognizing Textual Entailment (RTE) catches strongly the attention of the Natural Language Processing (NLP) community. Using Similarity is an useful method for RTE, in which the Judgment Threshold plays an important role as the learning model. This paper proposes an RTE model based on using similarity. We describe clearly the solutions to determine and to refine the Judgment Threshold for Improvement RTE. The measure of the synonym similarity also is considered. Experiments on a Vietnamese version of the RTE3 corpus are showed. Content Type Book ChapterPages 335-344DOI 10.1007/978-3-642-34707-8_34Authors Quang-Thuy Ha, College of Technology (UET), Vietnam ...
Mentions: Hanoi RTE Vietnam National University