A Survey of Paraphrasing and Textual Entailment Methods

Abstract

Paraphrasing methods recognize, generate, or extract phrases, sentences, or longer natural language expressions that convey almost the same information. Textual entailment methods, on the other hand, recognize, generate, or extract pairs of natural language expressions, such that a human who reads (and trusts) the first element of a pair would most likely infer that the other element is also true. Paraphrasing can be seen as bidirectional textual entailment and methods from the two areas are often similar. Both kinds of methods are useful, at least in principle, in a wide range of natural language processing applications, including question answering, summarization, text generation, and machine translation. We summarize key ideas from the two areas by considering in turn recognition, generation, and extraction methods, also pointing to prominent articles and resources.

Technical Report, Natural Language Processing Group, Department of Informatics, Athens University of Economics and Business, Greece, 2010

References in corpus (4)

• From Frequency to Meaning: Vector Space Models of Semantics
• Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language
• Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment
• PRINCIPAR---An Efficient, Broad-coverage, Principle-based Parser

Cited by in corpus (2)

• Experiments with Three Approaches to Recognizing Lexical Entailment
• Exploring Lexical, Syntactic, and Semantic Features for Chinese Textual Entailment in NTCIR RITE Evaluation Tasks