Browse Books

This book introduces the applied notion of textual entailment as a generic empirical task that captures major semantic inferences across many applications. Textual Entailment addresses semantic inference as a direct mapping between language expressions and abstracts the common semantic inferences as needed for text based Natural Language Processing applications. The book defines the task and describes the creation of a benchmark dataset for textual entailment along with proposed evaluation measures. It further describes how textual entailment can be approximated and modeled at the lexical level and proposes a lexical reference subtask and a correspondingly derived dataset. The book further proposes a general probabilistic setting that casts the applied notion of textual entailment in probabilistic terms. This proposed setting may provide a unifying framework for modeling uncertain semantic inferences from texts. Finally, the book presents a novel acquisition algorithm to identify lexical entailment relations from a single corpus focusing on the extraction of verb paraphrases.