Learning paraphrases from WNS corpora

• Type: Article in International Conference Proceedings Book
• Date: 2007

Authors

Cordeiro, J (Author) Other; Dias, G (Author) Other; Pavel Brazdil (Author) FEP

Conference proceedings International

Title: Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007

Pages: 193-198

20th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007

Key West, FL, 7 May 2007 through 9 May 2007

Indexing

Scopus - 3 Citations

Other information

Authenticus ID: P-007-K3D

Abstract (EN): Paraphrase detection can be seen as the task of aligning sentences that convey the same information but yet are written in different forms. Such resources are important to automatically learn text-to-text rewriting rules. In this paper, we present a new metric for unsupervised detection of paraphrases and apply it in the context of clustering of paraphrases. An exhaustive evaluation is conducted over a set of standard paraphrase corpora and real-world web news stories (WNS) corpora. The results are promising as they outperform state-of-the-art measures developed for similar tasks. Copyright

Language: English

Type (Professor's evaluation): Scientific