Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
Current statistical speech translation approaches predominantly rely on just text transcripts and do not adequately utilize the rich contextual information such as conveyed through prosody and discourse function. In this paper, we explore the role of context characterized through dialog acts (DAs) in statistical translation. We demonstrate the integration of the dialog acts in a phrase-based statistical translation framework, employing 3 limited domain parallel corpora (Farsi-English, Japanese-English and Chinese-English). For all three language pairs, in addition to producing interpretable DA enriched target language translations, we also obtain improvements in terms of objective evaluation metrics such as lexical selection accuracy. | Enriching spoken language translation with dialog acts Vivek Kumar Rangarajan Sridhar Srinivas Bangalore Shrikanth Narayanan AT T Labs - Research Speech Analysis and Interpretation Laboratory 180 Park Avenue University of Southern California Florham Park NJ 07932 U.S.A. vrangara@usc.edu shri@sipi.usc.edu srini@research.att.com Abstract Current statistical speech translation approaches predominantly rely on just text transcripts and do not adequately utilize the rich contextual information such as conveyed through prosody and discourse function. In this paper we explore the role of context characterized through dialog acts DAs in statistical translation. We demonstrate the integration of the dialog acts in a phrase-based statistical translation framework employing 3 limited domain parallel corpora Farsi-English Japanese-English and Chinese-English . For all three language pairs in addition to producing interpretable DA enriched target language translations we also obtain improvements in terms of objective evaluation metrics such as lexical selection accuracy and BLEU score. 1 Introduction Recent approaches to statistical speech translation have relied on improving translation quality with the use of phrase translation Och and Ney 2003 Koehn 2004 . The quality of phrase translation is typically measured using n-gram precision based metrics such as BLEU Papineni et al. 2002 and NIST scores. However in many dialog based speech translation scenarios vital information beyond what is robustly captured by words and phrases is carried by the communicative act e.g. question acknowledgement etc. representing the function of the utterance. Our approach for incorporating dialog act tags in speech translation is motivated by the fact that it is important to capture and convey not only what is being communicated the words but how something is being communicated the context . Augmenting current statistical translation frameworks with dialog acts can potentially improve translation
