Please use this identifier to cite or link to this item:
|Title:||An empirical study of statistical language models for contextual post-processing of Chinese script recognition|
|Authors:||Li, Y.-X. |
|Citation:||Li, Y.-X.,Tan, C.L. (2004). An empirical study of statistical language models for contextual post-processing of Chinese script recognition. Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR : 257-262. ScholarBank@NUS Repository. https://doi.org/10.1109/IWFHR.2004.15|
|Abstract:||It is crucial to use statistical language models (LMs) to improve the accuracy of Chinese offline script recognition. In this paper, we investigate the influence of several LMs on the contextual post-processing performance of Chinese script recognition. We first introduce seven LMs, i.e., three conventional LMs (character-based bigram, character-based trigram, word-based bigram), two class-based bigram LMs and two hybrid bigram LMs combining word-based bigrams and class-based bigrams. We then investigate how the LMs' perplexities are affected by training corpus size, smoothing methods and count cutoffs. Next, we demonstrate the above LMs' influence on the post-processing performance in terms of recognition accuracy, memory requirement and processing speed. Finally, we give a proposal to select a suitable LM in real recognition tasks. © 2004 IEEE.|
|Source Title:||Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 17, 2018
checked on Mar 10, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.