Sciweavers

IJCNLP
2004
Springer

Detection of Incorrect Case Assignments in Paraphrase Generation

14 years 4 months ago
Detection of Incorrect Case Assignments in Paraphrase Generation
Abstract. This paper addresses the issue of post-transfer process in paraphrasing. Our previous investigation into transfer errors revealed that case assignment tends to be incorrect, irrespective of the types of transfer in lexical and structural paraphrasing of Japanese sentences [3]. Motivated by this observation, we propose an empirical method to detect incorrect case assignments. Our error detection model combines two error detection models that are separately trained on a large collection of positive examples and a small collection of manually labeled negative examples. Experimental results show that our combined model significantly enhances the baseline model which is trained only on positive examples. We also propose a selective sampling scheme to reduce the cost of collecting negative examples, and confirm the effectiveness in the error detection task.
Atsushi Fujita, Kentaro Inui, Yuji Matsumoto
Added 02 Jul 2010
Updated 02 Jul 2010
Type Conference
Year 2004
Where IJCNLP
Authors Atsushi Fujita, Kentaro Inui, Yuji Matsumoto
Comments (0)