頁籤選單縮合
題名 | 語言模型調適技術概觀=A Survey of Language Model Adaptation Techniques |
---|---|
作者 | 邱中人; | 書刊名 | 電腦與通訊 |
卷期 | 133 2010.06[民99.06] |
頁次 | 頁75-80 |
分類號 | 312.85 |
關鍵詞 | 語言模型調適技術; 模型內插法; 動態邊際機率; 潛藏語意邊際機率; Language model adaptation techniques; Model interpolation; Dynamic marginals; Latent semantic marginals; |
語文 | 中文(Chinese) |
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. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。