隨著網際網路的普及，數之不盡的文本以及多媒體內容已經充斥於我們的日常生活當中。如何有效的獲取所需的知識變成不可避免的議題之一。為了幫助人們更快速地瀏覽和吸收文件的主題，許多研究致力於自動文件摘要(Automatic Document Summarization)，期望濃縮並盡可能保留文件之重要內容，其中又可分為節錄式(Extractive)摘要及重寫式(Abstractive)摘要。節錄式摘要直接從原始文件選取最為相關內容至一定的比例作為摘要；重寫式摘要則為理解文章內容後重新撰寫符合文意之短文。近年來的研究當中可以觀察到使用著深層類神經網路(Deep Neural Network)模型的監督式學習方法被高度關注並且運用在自動摘要的任務當中。本論文延續了這樣的研究，應用摺積式類神經網路(Convolutional Neural Network)、長短期記憶體(Long Short-Term Memory)及多層感知器(Multilayer Perceptron)提出兩種模型於節錄式語音文件摘要，並且與一些其他常見的模型比較後，從結果上顯示類神經網路模型可以得到更好的摘要能力。最後為了更了解類神經網路的能力，我們初步的實驗及分析了應用序列至序列型類神經網路(Sequence to Sequence Neural Network)於重寫式摘要之結果。

With the Internet becoming widespread, countless Articles and multimedia content has been filled with our daily life. How to effectively acquire the knowledge we needed becomes one of the unavoidable issues. To help people to browse the main theme of the document faster, many studies are dedicated to automatic document summarization, which aims to condense one or more documents into a short text yet still keep its essential content as much as possible. Automatic document summarization can be categorized into extractive and abstractive. Extractive summarization selects the most relevant set of sentences to a target ratio and assemble them into a concise summary. On the other hand, abstractive summarization produces an abstract after understanding the key concept of a document. The recent past has seen a surge of interest in developing deep neural network-based supervised methods for both automatic summarizations. This thesis presents a continuation of this line and exploit two kinds of frameworks, which integrate convolutional neural network (CNN), Long Short-Term Memory (LSTM) and multilayer perceptron (MLP) for extractive speech summarization. The empirical results seem to demonstrate the effectiveness of neural summarizers when compared with other supervised methods. Finally, to further explore the ability of neural network, we experiment and analyze the results of sequence-to-sequence neural network for abstractive summarization.

Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. International Conference on Learning Representations (ICLR).
Barzilay, R., & McKeown, K. R. (2005, 3 31). Sentence Fusion for Multidocument News Summarization. Computational Linguistics, pp. 297-328.
Baxendale, P. B. (1958, 2 4). Machine-made index for technical literature—an experiment. IBM Journal of Research and Development 2.4 , pp. 354-361.
Boersma, P. (2001). Praat. A system for doing phonetics by computer. Glot International, 5, pp. 341-345.
Bordes, A., Weston, J., & Nicolas, U. (2014). Open Question Answering with Weakly Supervised Embedding Models. ECML PKDD.
Boudin, F., & Morin, E. (2013). Keyphrase Extraction for N-best reranking in multi-sentence compression. North American Chapter of the Association for Computational Linguistics (NAACL).
Brian, R., Murat, S., & Michael, C. (2004). Corrective language modeling for large vocabulary ASR with the perceptron algorithm. Acoustics, Speech, and Signal Processing, 2004. Proceedings.(ICASSP'04). IEEE International Conference. IEEE.
Brian, R., Murat, S., & Michael, C. (2007, 2 21). Discriminative n-gram language modeling. Computer Speech & Language, pp. 373-392.
Cao, Y., Xu, J., Liu, T.-Y., Li, H., Yalou, H., & Hsiao-Wuen, H. (2006). Adapting ranking SVM to document retrieval. Proceeding SIGIR '06 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval (pp. 186-193). New York: ACM.
Cao, Z., Furu, W., Dong, L., Li, S., & Zhou, M. (2015). Ranking with Recursive Neural Networks and Its Application to Multi-Document Summarization. AAAI, (pp. 2153-2159). Austin, Texas.
Carbonell, J., & Goldstein, J. (1998). The use of MMR, diversity-based reranking for reordering documents and producing summaries. Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval. (pp. pp. 335-336). Melbourne, Australia: ACM.
Chen, K.-Y., Liu, S.-H., Chen, B., Wang, H.-M., Jan, E.-E., Hsu, W.-L., & Chen, H.-H. (2015 , 8 23). Extractive broadcast news summarization leveraging recurrent neural network language modeling techniques. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) , pp. 1322-1344.
Chen, Y.-T., Chen, B., & Wang, H.-M. (2009, 1 17). A probabilistic generative framework for extractive broadcast news speech summarization. IEEE Transactions on Audio, Speech, and Language Processing, pp. 95-106.
Cheng, J., & Lapata, M. (2016). Neural Summarization by Extracting Sentences and Words. ACL.
Chien, J.-T. (2015, 8 23). Hierarchical Pitman-Yor-Dirichlet language model . IEEE Transactions on Audio, Speech, and Language Processing , pp. 1259-1272.
Chopra, S., Auli, M., & Rush, A. M. (2016). Abstractive Sentence Summarization with Attentive Recurrent Neural Networks. HLT-NAACL.
Chuang, W. T., & Jihoon, Y. (2000). Extracting sentence segments for text summarization: a machine learning approach. SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval (pp. 152-159). New York: ACM.
Crammer, K., & Singer, Y. (2002). Pranking with ranking. Advances in neural information processing systems. (pp. 641-647). MIT Press.
Earl, L. L. (1970, 6 4). Experiments in automatic extracting and indexing. Information Storage and Retrieval , pp. 313-330.
Edmundson, H. P. (1969, 2 16). New methods in automatic extracting. Journal of the ACM (JACM), pp. 264-285.
Eduard, H., & Lin, C.-Y. (1998). Automated text summarization and the SUMMARIST system. TIPSTER (pp. 197-214). Baltimore, Maryland: Association for Computational Linguistics.
Elke, M., & Peter, S. (1994). Document and passage retrieval based on hidden Markov models. SIGIR conference on Research and development in information retrieval (pp. 318-327). New York: Springer-Verlag.
Filippova, K. (2010). Multi-sentence compression: finding shortest paths in word graphs. COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics (pp. 322-330). Association for Computational Linguistics.
Furui, S., Deng, L., Mark, G., Ney, H., & Tokuda, K. (2012). Fundamental technologies in modern speech recognition. IEEE Signal Processing Magazine.
Gabriel, M., Steve, R., & Carletta, J. (2005). Extractive summarization of meeting recordings. European Conference on Speech Communication and Technology. INTERSPEECH.
Galley, M. (2006). A skip-chain conditional random field for ranking meeting utterances by importance. Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (pp. 364-372). Association for Computational Linguistics.
Galley, M., Kathleen, M., Julia, H., & Elizabeth, S. (2004). Identifying agreement and disagreement in conversational speech: use of Bayesian networks to model pragmatic dependencies. ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics (pp. 669-676). Association for Computational Linguistics.
Gerald, P., & Zhu, X. (2008). A Critical Reassessment of Evaluation Baselines for Speech Summarization. ACL. (pp. 470-478). Association for Computational Linguistics.
Graves, A., Jaitly, N., & Mohamed, A.-r. (2013). Hybrid speech recognition with deep bidirectional LSTM. Automatic Speech Recognition and Understanding. IEEE.
Gupta, V., & Lehal, G. (2010). A Survey of Text Summarization Extractive Techniques. Journal of emerging technologies in web intelligence.
Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A.-r., Jaitly, N., . . . Kingsbury, B. (2012, 6 29). Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Processing Magazine , 82-97.
Hori, C., & Furui, S. (2004, 01 01). Speech summarization: an approach through word extraction and a method for evaluation. IEICE TRANSACTIONS on Information and Systems, pp. 15-25.
Hovy, E., & Lin, C.-Y. (1998). Automated text summarization and the SUMMARIST system. TIPSTER (pp. 197-214 ). Baltimore, Maryland: Association for Computational Linguistics.
Huang, C.-L., & Wu, C.-H. (2007, 8 15). Spoken Document Retrieval Using Multilevel Knowledge and Semantic Verification . IEEE Transactions on Audio, Speech, and Language Processing, pp. 2551-2560.
Inderjeet, M., & (ed.), M. M. (1999). Advances in automatic text summarization. Cambridge, MA: MIT press.
Jaime, C., & Goldstein, J. (1998). The use of MMR, diversity-based reranking for reordering documents and producing summaries. Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval. (pp. pp. 335-336). ACM.
Julian, M. K., Jan, P., & Chen, F. (1995). A trainable document summarizer. Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval. (pp. 68-73). ACM.
Kågebäck, M., Mogren, O., Tahmasebi, N., & Dubhashi, D. (2014). Extractive Summarization using Continuous Vector Space Models. Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC).
Knight, K., & Daniel, M. (2000). Statistics-based summarization-step one: Sentence compression. AAAI/IAAI 2000 (pp. 703-710). AAAI Press.
Koby, C., & Singer, Y. (2002). Pranking with ranking. Advances in neural information processing systems. (pp. 641-647). MIT Press.
Konstantinos, K., & Renals, S. (2000). Transcription and summarization of voicemail speech. International Conference on Spoken Language Processing.
Korbinian, R., Favre, B., & Hakkani-Tür, D. (2010). Long story short–global unsupervised models for keyphrase based meeting summarization. Speech Communication , 52(10), pp. 801-815.
Kuo, J.-J., & Chen, H.-H. (2008, 2). Multidocument summary generation: Using informative and event words. ACM Transactions on Asian Language Information Processing (TALIP), 7(1), 3., pp. 1-23.
Kupiec, J., Pedersen, J., & Chen, F. (1995). A trainable document summarizer. Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval. (pp. 68-73). ACM.
Lee, L.-s., & Chen, B. (2005, 5 22). Spoken document understanding and organization. IEEE Signal Processing Magazine, 42-60.
Lin, C.-Y. (2003). ROUGE: Recall-oriented understudy for gisting evaluation. In Proceedings of the Workshop on Text Summarization.
Lin, H., & Bilmes, J. (2010). Multi-document summarization via budgeted maximization of submodular functions. HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics (pp. 912-920). Association for Computational Linguistics.
Lin, S.-H., Chen, B., & Wang, H.-M. (2009, 1 8). A comparative study of probabilistic ranking models for Chinese spoken document summarization. ACM Transactions on Asian Language Information Processing (TALIP), pp. 3:1-3:23.
Liu, S.-H., Chen, K.-Y., Chen, B., Jan, E.-E., Wang, H.-M., Yen, H.-C., & Hsu, W.-L. (2014). A margin-based discriminative modeling approach for extractive speech summarization. Asia-Pacific Signal and Information Processing Association, 2014 Annual Summit and Conference (APSIPA) (pp. 1-6). IEEE.
Liu, S.-H., Chen, K.-Y., Chen, B., Wang, H.-M., Yen, H.-C., & Hsu, W.-L. (2015, 23 6). Combining relevance language modeling and clarity measure for extractive speech summarization. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), pp. 957-969.
Liu, Y., & Hakkani‐Tür, D. (2011). Speech Summarization. In Speech summarization. Spoken language understanding: Systems for extracting semantic information from speech (pp. 357-396).
Liu, Y., & Xie, S. (2008). Impact of automatic sentence segmentation on meeting summarization. International Conference on Acoustics, Speech and Signal Processing (pp. 5009-5012). IEEE.
Liu, Y., Shriberg, E., Stolcke, A., Hillard, D., Ostendorf, M., & Harper, M. (2006, 5 14). Enriching speech recognition with automatic detection of sentence boundaries and disfluencies. IEEE Transactions on audio, speech, and language processing, pp. 1526-1540.
Luhn, H. P. (1958, 2 2). The automatic creation of literature abstracts. IBM Journal of research and development, pp. 159-165.
Luong, M.-T., Pham, H., & Manning, C. D. (2015). Effective Approaches to Attention-based Neural Machine Translation. EMNLP.
Mahmood, Y.-A., & Hamey, L. (2017, 2). Text summarization using unsupervised deep learning. Expert Systems with Applications, 68, pp. 93-105.
Mani, I., & Maybury, M. T. (1999). Advances in automatic text summarization. Cambridge, MA: MIT press.
Mari, O. (2008, 3 25). Speech technology and information access. IEEE Signal Processing Magazine, 152-150.
Maskey, S., & Hirschberg, J. (2005). Comparing lexical, acoustic/prosodic, structural and discourse features for speech summarization. Interspeech, (pp. 621-624).
McDonald, R. (2007). A study of global inference algorithms in multi-document summarization. European Conference on Information Retrieval. (pp. 557-564). Berlin Heidelberg: Springer.
McKeown, K., Hirschberg, J., Galley, M., & Maskey, S. (2005). From text to speech summarization. In Acoustics, Speech, and Signal Processing, 2005. Proceedings.(ICASSP'05). (pp. 997-1000). IEEE .
Michel, G. (2006). A skip-chain conditional random field for ranking meeting utterances by importance. Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (pp. 364-372). Association for Computational Linguistics.
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed Representations of Words and Phrases and their Compositionality. Advances in neural information processing systems. Curran Associates Inc.
Mittendorf, E., & Schäuble, P. (1994). Document and passage retrieval based on hidden Markov models. Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval (pp. 318-327). New York: Springer-Verlag.
Murray, G., Renals, S., & Carletta, J. (2005). Extractive summarization of meeting recordings. Interspeech.
Nallapati, R., Zhai, F., & Zhou, B. (2017). SummaRuNNer: A recurrent neural network based sequence model for extractive summarization of documents. In Association for the Advancement of Artificial Intelligence.
Nallapati, R., Zhou, B., dos santos, C., & Xiang, B. (2016). Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond. The SIGNLL Conference on Computational Natural Language Learning (CoNLL).
Neto, J. L., Freitas, A., & Kaestner, C. (2002). Automatic text summarization using a machine learning approach. Brazilian Symposium on Artificial Intelligence (pp. 205-215). Berlin Heidelberg.: Springer.
Ono, K., Sumita, K., & Miike, S. (1994). Abstract generation based on rhetorical structure extraction. Proceeding COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1 (pp. 344-348 ). Association for Computational Linguistics .
Ostendorf, M. (2008, 3 25). Speech technology and information access. IEEE Signal Processing Magazine, 152-150.
Ostendorf, M., Favre, B., Grishman, R., Hakkani-Tur, D., Harper, M., Hillard, D., . . . Wooters, C. (2008, 3 25). Speech segmentation and spoken document processing. IEEE Signal Processing Magazine, 59-69.
Paice, C. D. (1990, 1 26). Constructing literature abstracts by computer: Techniques and prospects. Information Processing & Management .
Penn, G., & Xiaodan, Z. (2008). A Critical Reassessment of Evaluation Baselines for Speech Summarization. ACL., (pp. 470-478).
Pennington, J., Socher, R., & Manning, C. D. (2014). Glove: Global vectors for word representation. EMNLP, 14.
Ren, P., Wei, F., Chen, Z., Ma, J., & Zhou, M. (2016). A Redundancy-Aware Sentence Regression Framework for Extractive Summarization. COLING.
Riedhammer, K., Favre, B., & Hakkani-Tür, D. (2010). Long story short–global unsupervised models for keyphrase based meeting summarization. Speech Communication, 52(10), pp. 801-815.
Roark, B., Saraclar, M., & Collins, M. (2004). Corrective language modeling for large vocabulary ASR with the perceptron algorithm. Acoustics, Speech, and Signal Processing, 2004. Proceedings.(ICASSP'04). IEEE International Conference. IEEE.
Roark, B., Saraclar, M., & Collins, M. (2007, 2 21). Discriminative n-gram language modeling. Computer Speech & Language, pp. 373-392.
Rush, A. M., Sumit, C., & Jason, W. (2016). A neural attention model for abstractive sentence summarization. The SIGNLL Conference on Computational Natural Language Learning (CoNLL).
Ryan, M. (2007). A study of global inference algorithms in multi-document summarization. European Conference on Information Retrieval. (pp. 557-564). Berlin Heidelberg: Springer.
Saggion, H., & Lapalme, G. (2002, 4 28). Generating Indicative-Informative Summaries with SumUM. Computational Linguistics, pp. 497-526.
Sameer, M., & Hirschberg, J. (2005). Comparing lexical, acoustic/prosodic, structural and discourse features for speech summarization. Interspeech, (pp. 621-624).
See, A., Liu, P. J., & Manning, C. D. (2017). Get To The Point: Summarization with Pointer-Generator Networks. Association for Computational Linguistics, (pp. 1073-1083).
Severyn, A., & Moschitti, A. (2015). Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 373-382). ACM.
Simonyan, K., & Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. ICLR.
Vapnik, V. N., & Vapnik, V. (1998). Statistical learning theory (Vol. 1). New York: Wiley.
Wang, H.-m., Chen, B., Kuo, J.-W., & Cheng, S.-S. (2005, 2 10). MATBN: A Mandarin Chinese broadcast news corpus. International Journal of Computational Linguistics and Chinese Language Processing.
White, M., Korelsky, T., Cardie, C., Ng, V., Pierce, D., & Wagstaff, K. (2001). Multidocument summarization via information extraction. HLT '01 Proceedings of the first international conference on Human language technology research, 1-7.
Xu, K., Ba, J. L., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., . . . Bengio, Y. (2015). Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. International Conference on Machine Learning. (pp. 2048-2057). JMLR.org.
Yan, L., Zhong, S.-h., & Li, W. (2012). Query-Oriented Multi-Document Summarization via Unsupervised Deep Learning. AAAI.
Yang, L., & Xie, S. (2008). Impact of automatic sentence segmentation on meeting summarization. Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. (pp. 5009-5012). IEEE .
Yousefi-Azar, M., & Hamey, L. (2017, 2). Text summarization using unsupervised deep learning. Expert Systems with Applications, 68, pp. 93-105.
Yousfi-Monod, M. (2007). Compression automatique ou semi-automatique de textes par élagage des constituants effaçables: une approche interactive et indépendante des corpus. (Doctoral dissertation, Université Montpellier II-Sciences et Techniques du Languedoc).
Zhang, J. J., Chan, H. Y., & Fung, P. (2007). Improving lecture speech summarization using rhetorical information. utomatic Speech Recognition & Understanding, 2007 ASRU (pp. 195-200). IEEE.
Zhang, J., Chan, H., Fung, P., & Cao, L. (2007). "A comparative study on speech summarization of broadcast news and lecture speech. Interspeech, (pp. 2781-2784).