Authors
Erel Segal-haLevi, Ido Dagan, Israel Ramat-Gan
Description
One of the components of a dialog system is the Natural Language Understanding (NLU) component. This component accepts natural language text, and returns the meaning of that text, in some formal application-specific meaning representation. One of the difficulties in building NLU components is the variability in natural language-the many different ways by which a human can express the same meaning. We propose to tackle this difficulty by using a generic Textual Entailment (TE) system-a system that can calculate, for each pair of texts, whether the meaning of one of them can be inferred from the other. A single TE system can be used for various NLU components in various domains.
Scholar articles