Toutanova, Kristina and Moore, Robert (2002) Pronunciation Modeling for Improved Spelling Correction. In: 40th Annual Meeting of the Association for Computational Linguistics(ACL 2002), July 6-12, 2002, Philadelphia, PA.
| BibTeX | DublinCore | EndNote | HTML |
![[img]](/style/images/fileicons/application_pdf.png)
| PDF 76Kb |
Abstract
This paper presents a method for incorporating word pronunciation information in a noisy channel model for spelling correction. The proposed method builds an explicit error model for word pronunciations. By modeling pronunciation similarities between words we achieve a substantial performance improvement over the previous best performing models for spelling correction.
| Item Type: | Conference or Workshop Item (Paper) | |
|---|---|---|
| Uncontrolled Keywords: | spelling correction, letter-to-sound models, noisy channel modeling | |
| Subjects: | Miscellaneous | |
| Projects: | Miscellaneous | |
| Related URLs: | Project Homepage | http://www-nlp.stanford.edu/ |
| ID Code: | 556 | |
| Deposited By: | Import Account | |
| Deposited On: | 16 Oct 2002 17:00 | |
| Last Modified: | 25 Dec 2008 10:20 |
Download statistics
Repository Staff Only: item control page
