Paraphrase (Computational Linguistics)
- For the linguistics definition, see paraphrase.
Paraphrase or Paraphrasing in computational linguistics is the natural language processing task of detecting and generating paraphrases.
Applications of paraphrasing are varied including information retrieval, question answering, text summarization, and plagiarism detection.[1] Paraphrasing is also useful in the evaluation of machine translation[2], as well as generation of new samples to expand existing corpora.[3]
Paraphrase models are often trained through the usage of parallel text such as news articles covering the same incident or translations of novels. Since a desired output is not given, the training of paraphrase models is an instance of unsupervised learning.
Training
Sequence Alignment
Translation
Autoencoders
Skip-Thought Vectors
References
- ^ a b Socher, Richard; Huang, Eric; Pennington, Jeffrey; Ng, Andrew; Manning, Christopher (2011), Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection
{{citation}}: Unknown parameter|booktitle=ignored (help) - ^ Callison-Burch, Chris (October 25–27, 2008). "Syntactic Constraints on Paraphrases Extracted from Parallel Corpora". EMNLP '08 Proceedings of the Conference on Empierical Methods in Natural Language Processing. Honolulu, Hawaii. pp. 196–205.
{{cite conference}}: CS1 maint: date format (link) - ^ a b Barzilay, Regina; Lee, Lillian (May–June 2003). "Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment". Proceedings of HLT-NAACL 2003.
{{cite conference}}: CS1 maint: date format (link) - ^ Bannard, Colin; Callison-Burch, Chris (2005). "Paraphrasing Bilingual Parallel Corpora". Proceedings of the 43rd Annual Meeting of the ACL. Ann Arbor, Michigan. pp. 597–604.
{{cite conference}}: Unknown parameter|booktitle=ignored (|book-title=suggested) (help) - ^ Kiros, Ryan; Zhu, Yukun; Salakhutdinov, Ruslan; Zemel, Richard; Torralba, Antonio; Urtasun, Raquel; Fidler, Sanja (2015), Skip-Thought Vectors