文章詳目資料

電腦與通訊

  • 加入收藏
  • 下載文章
篇名 語言模型調適技術概觀
卷期 133
並列篇名 A Survey of Language Model Adaptation Techniques
作者 邱中人
頁次 75-80
關鍵字 語言模型調適技術Language Model Adaptation Techniques模型內插法Model Interpolation動態邊際機率Dynamic Marginals潛藏語意邊際機率Latent Semantic Marginals
出刊日期 201006

中文摘要

近年來,語言模型已經被應用到許多語言及語音相關技術,如語音辨識,語音合成,資訊檢
索,機器翻譯與文字辨識等等。然而隨著語言文字演化,新的詞彙與片語不斷地被創造出來,如
雲端運算…等。此外相同的詞彙與片語,在不同領域,不同時間或不同情況下,語意也都不盡相
同。由於這些變化,語言模型調適技術逐漸受到重視。本篇論文中,我們將介紹一些主要的語言
模型調適技術,分析並比較這些技術的特點。

英文摘要

In recent years, language model has been utilized language and speech processing , such as speech recognition, speech synthesis, information retrieval, machine translation, optical character recognition and so
on. Since, natural language is highly diversified, new words, e.g., cloud computing, and new phrases are created constantly. Moreover, in different areas, different time or different circumstances, same words or
same phrases may have different semantic meaning. Because of these varieties, language model adaptation is becoming more and more important. In this paper, we will introduce some techniques of language model
adaptation and give a detail analysis and comparison.

本卷期文章目次

相關文獻