節錄式語音文件摘要使用表示法學習技術

Extractive Spoken Document Summarization with Representation Learning Techniques

施凱文(Kai-Wun Shih) ； 陳冠宇(Kuan-Yu Chen) ； 劉士弘(Shih-Hung Liu) ； 王新民(Hsin-Min Wan) ； 陳柏琳(Berlin Chen))

《中文計算語言學期刊》 20卷2期 (2015/12) Pp. 65-85

摘要

大量多媒體內容的與日俱增促使自動語音文件摘要成為一項重要的研究議題。其中最為廣泛地被探究的是節錄式語音文件摘要(Extractive Spoken Document Summarization)，其目的是根據事先定義的摘要比例，從語音文件中選取一些重要的語句，用以代表原始語音文件的主旨或主題。另一方面，表示法學習(Representation Learning)是近期相當熱門的一個研究議題，多數的研究成果也證明了這項技術在許多自然語言處理(Natural Language Processing, NLP)的相關任務上，可以進一步地獲得優良的成效。有鑑於此，本論文主要探討使用詞表示法(Word Representations)及語句表示法(Sentence Representations)於節錄式中文廣播新聞語音文件摘要之應用。基於詞表示法及語句表示法，本論文提出三種新穎且有效的排序模型(Ranking Models)。除了文件中的文字資訊外，本論文更進一步地結合語音文件上的各式聲學特徵，如韻律特徵(Prosodic Features)等，期望可以獲得更好的摘要成效。本論文的語音文件摘要實驗語料是採用公視廣播新聞；實驗結果顯示，相較於其它現有的摘要方法，我們所發展的新穎式摘要方法能夠提供顯著的效能改善。

關鍵字

語音文件 ； 節錄式摘要 ； 詞表示法 ； 語句表示法 ； 韻律特徵

並列摘要

The rapidly increasing availability of multimedia associated with spoken documents on the Internet has prompted automatic spoken document summarization to be an important research subject. Thus far, the majority of existing work has focused on extractive spoken document summarization, which selects salient sentences from an original spoken document according to a target summarization ratio and concatenates them to form a summary concisely, in order to convey the most important theme of the document. On the other hand, there has been a surge of interest in developing representation learning techniques for a wide variety of natural language processing (NLP)-related tasks. However, to our knowledge, they are largely unexplored in the context of extractive spoken document summarization. With the above background, this study explores a novel use of both word and sentence representation techniques for extractive spoken document summarization. In addition, three variants of sentence ranking models building on top of such representation techniques are proposed. Furthermore, extra information cues like the prosodic features extracted from spoken documents, apart from the lexical features, are also employed for boosting the summarization performance. A series of experiments conducted on the MATBN broadcast news corpus indeed reveal the performance merits of our proposed summarization methods in relation to several state-of-the-art baselines.

並列關鍵字

Spoken Document ； Extractive Summarization ； Word Representation ； Sentence Representation ； Prosodic Feature

參考文獻

Wang, H.-M.,Chen, B.,Kuo, J.-W.,Cheng, S.-S.(2005).MATBN: a Mandarin Chinese broadcast news corpus.Journal of Computational Linguistics and Chinese Language Processing.10(2),219-236.

Bengio, Y.,Ducharme, R.,Vincent, P.,Jauvin, C.(2003).A neural probabilistic language model.Journal of Machine Learning Research.3,1137-1155.

Carbonell, J.,Goldstein, J.(1998).The use of MMR, diversity-based reranking for reordering documents and producing summaries.Proceedings of the Annual International ACM Conference on Research and Development in Information Retrieval.(Proceedings of the Annual International ACM Conference on Research and Development in Information Retrieval).

Chen, Y.-T.,Chen, B.,Wang, H.-M.(2009).A probabilistic generative framework for extractive broadcast news speech summarization.IEEE Transactions on Audio, Speech and Language Processing.17(1),95-106.

Gong, Y.,Liu, X.(2001).Generic text summarization using relevance measure and latent semantic analysis.Proceedings of the Annual International ACM Conference on Research and Development in Information Retrieval.19-25.