Author Description

As researchers try to build on existing research in Natural Language Processing (NLP), they are finding that Natural Language Understanding (NLU) is important not only in high-level tasks like semantic search, where the goal is to access concepts instead of keywords, but also in low-level semantic tagging tasks such as Named Entity Recognition. Understanding (to some extent) the context of terms of interest is needed to decide whether or not an entity/concept of interest is present, however the author phrased it. In the last few years, a number of NLP researchers have developed and participated in the task of Recognizing Textual Entailment. This task encapsulates Natural Language Understanding capabilities within a very simple interface: that of recognizing when the meaning of one piece of text is contained in the meaning of a second piece of text. This simple abstraction of an exceedingly complex problem has broad appeal because it can as a result be conceived of as a component in other NLP applications, including Machine Translation and Semantic Search. It also avoids commitment to any specific meaning representation and reasoning framework, broadening its appeal within the research community. This extreme level of abstraction also facilitates evaluation, a crucial component of any technological advancement program. This book explains the RTE task formulation adopted by the NLP research community, and gives a clear overview of research in this area. It draws out commonalities in this research, detailing the intuitions behind dominant approaches and giving their theoretical underpinnings. The book has been written with a wide audience in mind, but is intended to inform all readers about the state of the art in this fascinating field, to give a clear understanding of the principles underpinning RTE research to date, and to highlight the short- and long-term research goals that will advance this technology.