ダウンロード数: 169

このアイテムのファイル:
ファイル 記述 サイズフォーマット 
transinf.E93.D.3359.pdf810.91 kBAdobe PDF見る/開く
タイトル: Selecting Help Messages by Using Robust Grammar Verification for Handling Out-of-Grammar Utterances in Spoken Dialogue Systems
著者: Komatani, Kazunori
Fukubayashi, Yuichiro
Ikeda, Satoshi
Ogata, Tetsuya
Okuno, Hiroshi G.
著者名の別形: 奥乃, 博
キーワード: spoken dialogue system
help generation
out-of-grammar utterances
novice user
utterance history
発行日: 1-Dec-2010
出版者: The Institute of Electronics, Information and Communication Engineers(IEICE)
誌名: IEICE Transactions Information and Systems
巻: E93-D
号: 12
開始ページ: 3359
終了ページ: 3367
抄録: We address the issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages. Help message generation for OOG utterances is a challenge because language understanding based on automatic speech recognition (ASR) of OOG utterances is usually erroneous; important words are often misrecognized or missing from such utterances. Our grammar verification method uses a weighted finite-state transducer, to accurately identify the grammar rule that the user intended to use for the utterance, even if important words are missing from the ASR results. We then use a ranking algorithm, RankBoost, to rank help message candidates in order of likely usefulness. Its features include the grammar verification results and the utterance history representing the user's experience.
著作権等: © 2010 The Institute of Electronics, Information and Communication Engineers
URI: http://hdl.handle.net/2433/187386
DOI(出版社版): 10.1587/transinf.E93.D.3359
出現コレクション:学術雑誌掲載論文等

アイテムの詳細レコードを表示する

Export to RefWorks


出力フォーマット 


このリポジトリに保管されているアイテムはすべて著作権により保護されています。