About this Computer Science article
An Empirical Study on Language Model Adaptation by Jianfeng Gao; Hisami Suzuki; Wei Yuan is a Computer Science article available to read on EtoBox.
This article presents an empirical study of four techniques for adapting language models, including a maximum __a posteriori__ (MAP) method and three discriminative training models, in the application of Japanese __Kana-Kanji__ conversion. We compare the performance of these methods from various angles by adapting the baseline model to four adaptation domains. In particular, we attempt to interpret the results in terms of the character error rate (CER) by correlating them with the characteristics of the adaptation domain, measured by using the information-theoretic notion of cross entropy. We show that such a metric correlates well with the CER performance of the adaptation methods, and also show that the discriminative methods are not only superior to a MAP-based method in achieving larger CER reduction, but also in having fewer side effects and being more robust against the similarity between background and adaptation domains.
It is typically read by researchers, students, and practitioners in Computer Science.
- Author
- Jianfeng Gao; Hisami Suzuki; Wei Yuan
- Publisher
- ACM
- Published
- 2006
- Language
- EN
- Field
- Computer Science (Physical Sciences)