关键词: 语言模型压缩 次数剪切 规则剪枝 分组 困惑度

Abstract:

Currently the size of most statistical language models based on large-scale training corpus always goes beyond the storage ability of many handheld de vices. With the rapid development of the limited resource devices, the research on language model compression can meet such requirements. This paper pro poses a language model compression method which combined the count cutoff and the pruning method to reduce the size of the language model and uses group ing to compress this model without cell reduction. Our experimental results show that our method can achieve higher perplexity than those of other metho   ds based on the same size.

Key words: language model compression, count cutoff, rule pruning, grouping, perplexity