@inproceedings{70d9680aef824762b793b2e30f24cc7b,
title = "A similarity-based approach to data sparseness problem of Chinese language modeling",
abstract = "Data sparseness problem is inherent and severe in language modeling. Smoothing techniques are usually widely used to solve this problem. However, traditional smoothing techniques are all based on statistical hypotheses without concerning about linguistic knowledge. This paper introduces semantic information into smoothing technique and proposes a similarity-based smoothing method which is based on both statistical hypothesis and linguistic hypothesis. An experiential iterative algorithm is presented to optimize system parameters. Experiment results prove that compared with traditional smoothing techniques, our method can greatly improve the performance of language model.",
author = "Jinghui Xiao and Bingquan Liu and Xiaolong Wang and Bing Li",
year = "2005",
doi = "10.1007/11579427\_77",
language = "英语",
isbn = "3540298967",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
pages = "761--769",
booktitle = "MICAI 2005",
note = "4th Mexican International Conference on Artificial Intelligence, MICAI 2005 ; Conference date: 14-11-2005 Through 18-11-2005",
}