A Survey of Paraphrasing and Textual Entailment Methods

Details A Survey of Paraphrasing and Textual Entailment Methods A Survey of Paraphrasing and Textual Entailment Methods

2009-12-18

arxiv.org/abs/0912.3747v3

I. Androutsopoulos and P. Malakasiotis, "A Survey of Paraphrasing and Textual Entailment Methods". Journal of Artificial Intel

Computer Science

Computation and Language

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

Scientific paper

10.1613/jair.2985

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.

Affiliated with

Also associated with

No associations

Rating

A Survey of Paraphrasing and Textual Entailment Methods does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Survey of Paraphrasing and Textual Entailment Methods, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Survey of Paraphrasing and Textual Entailment Methods will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-350105