This paper describes a method of task adaptation in N-gram language modeling, for accurately estimating the N-gram statistics from the small amount of data of the target task. Assuming a task-independent N-gram to be a-priori knowledge, the N-gram is adapted to a target task by MAP (maximum a-posteriori probability) estimation. Experimental results showed that the perplexities of the task adapted models were 15% (trigram), 24% (bigram) lower than those of the task-independent model, and that the perplexity reduction of the adaptation went up to 39% at maximum when the amount of text data in the adapted task was very small.
|ジャーナル||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|
|出版ステータス||Published - 1997 1月 1|
|イベント||Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5) - Munich, Ger|
継続期間: 1997 4月 21 → 1997 4月 24
ASJC Scopus subject areas