White Papers

An Empirical Study on Language Model Adaptation Using a Metric of Domain Similarity

• Tags:
• adaptation,
• training,
• techniques,
• terms

Overview This paper presents an empirical study on four techniques of language model adaptation, including a Maximum A Posteriori (MAP) method and three discriminative training models, in the application of Japanese Kana-Kanji conversion. The authors compare the performance of these methods from various angles by adapting the baseline model to four adaptation domains. In particular, they attempt to interpret the results given in terms of the Character Error Rate (CER) by correlating them with the characteristics of the adaptation domain measured using the information-theoretic notion of cross entropy.

• 
• Did you find this white paper useful?

• Subscribe to the IT White Papers Newsletter
• White Paper RSS