Abstract
The primary task of extractive summarization is to automatically select a set of representative sentences from a text or spoken document that can concisely express the most important theme of the original document. Recently, language modeling (LM) has been proven to be a promising modeling framework for performing this task in an unsupervised manner. However, there still remain three fundamental challenges facing the existing LM-based methods, which we set out to tackle in this article. The first one is how to construct a more accurate sentence model in this framework without resorting to external sources of information. The second is how to take into account sentence-level structural relationships, in addition to word-level information within a document, for important sentence selection. The last one is how to exploit the proximity cues inherent in sentences to obtain a more accurate estimation of respective sentence models. Specifically, for the first and second challenges, we explore a novel, principled approach that generates overlapped clusters to extract sentence relatedness information from the document to be summarized, which can be used not only to enhance the estimation of various sentence models but also to render sentence-level structural relationships within the document, leading to better summarization effectiveness. For the third challenge, we investigate several formulations of proximity cues for use in sentence modeling involved in the LM-based summarization framework, free of the strict bag-of-words assumption. Furthermore, we also present various ensemble methods that seamlessly integrate proximity and sentence relatedness information into sentence modeling. Extensive experiments conducted on a Mandarin broadcast news summarization task show that such integration of proximity and sentence relatedness information is indeed beneficial for speech summarization. Our proposed summarization methods can significantly boost the performance of an LM-based strong baseline (e.g., with a maximum ROUGE-2 improvement of 26.7% relative) and also outperform several state-of-the-art unsupervised methods compared in the article.
- S. Furui, L. Deng, M. Gales, H. Ney, and K. Tokuda. 2012. Fundamental technologies in modern speech recognition. IEEE Sign. Process. Mag. 29, 6 (2012), 16--17.Google Scholar
Cross Ref
- R. Blanco, G. D. F. Morales, and F. Silvestri. 2016. IntoNews: Online news retrieval using closed captions. Inf. Process. Manage. 51, 1 (2016), 148--162.Google Scholar
Cross Ref
- M. Ostendorf. 2008. Speech technology and information access. IEEE Sign. Process. Mag. 25, 3 (2008), 150--152.Google Scholar
Cross Ref
- L.-S. Lee and B. Chen. 2005. Spoken document understanding and organization. IEEE Sign. Process. Mag. 22, 5 (2005), 42--60.Google Scholar
Cross Ref
- D. Yu and L. Deng. 2015. Automatic Speech Recognition: A Deep Learning Approach. Springer.Google Scholar
- Y. Liu and D. Hakkani-Tur. 2011. Speech Summarization. Wiley, New York, NY.Google Scholar
- G. Penn and X. Zhu. 2008. A critical reassessment of evaluation baselines for speech summarization. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL’08), 470--478.Google Scholar
- A. Nenkova and K. McKeown. 2011. Automatic summarization, Found. Trends Inf. Retriev. 5, 2--3 (2011), 103--233.Google Scholar
Cross Ref
- I. Mani and M. T. Maybury. (Eds.) 1999. Advances in Automatic Text Summarization. MIT Press, Cambridge, MA.Google Scholar
- J.-M. Torres-Moreno (Ed.). 2014. Automatic Text Summarization. Wiley-ISTE, New York, NY.Google Scholar
- X. Zhu, G. Penn, and F. Rudzicz. 2009. Summarizing multiple spoken documents: Finding evidence from untranscribed audio. In Proceedings of the Joint Conference of Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP’09), 549--557.Google Scholar
- S.-H. Liu, H.-S. Lee, H.-T. Hung, K.-Y. Chen, B. Chen, H.-M. Wang, H.-C. Yen, and W.-L. Hsu. 2015. Incorporating proximity information in relevance language modeling for extractive speech summarization. In Proceedings of the APSIPA Annual Summit and Conference. 401--407.Google Scholar
Cross Ref
- A. Celikyilmaz and D. Hakkani-Tur. 2010. A hybrid hierarchical model for multi-document summarization. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL’10), 815--824.Google Scholar
- S.-H. Lin, Y.-M Yeh, and B. Chen. 2011. Leveraging Kullback-Leibler divergence measures and information-rich cues for speech summarization. IEEE Trans. Audio Speech Lang. Process. 19, 4 (2011), 871--882.Google Scholar
Digital Library
- S.-H. Liu, K.-Y. Chen, B. Chen, H.-M. Wang, H.-C. Yen, and W.-L Hsu. 2015. Combining relevance language modeling and clarity measure for extractive speech summarization. IEEE/ACM Trans. Audio Speech Lang. Process. 23, 6 (2015), pp. 957--969.Google Scholar
Digital Library
- P. B. Baxendale. 1958. Machine-made index for technical literature-an experiment. IBM J. 2, 3 (1958), 354--361.Google Scholar
Digital Library
- Y. Gong and X. Liu. 2001. Generic text summarization using relevance measure and latent semantic analysis. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’01), 19--25.Google Scholar
- M. Kagebäck, O. Mogren, N. Tahmasebi, and D. Dubhashi. 2014. Extractive summarization using continuous vector space models. In Proceedings of the Workshop on Continuous Vector Space Models and Their Composition, 31--39.Google Scholar
- X. Wan and J. Yang. 2008. Multi-document summarization using cluster-based link analysis. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’08), 299--306.Google Scholar
- S. Xiong and D. Ji. 2016. Query-focused multi-document summarization using hypergraph-based ranking. Inf Process. Manage. 52, 4 (2016), 670--681.Google Scholar
Digital Library
- J. Carbonell and J. Goldstein. 1998. The use of MMR, diversity based reranking for reordering documents and producing summaries. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’98), 335--336.Google Scholar
- S. Furui, T. Kikuchi, Y. Shinnaka, and C. Hori. 2004. Speech-to-text and speech-to-speech summarization of spontaneous speech. IEEE Trans. Speech Audio Process. 12, 4 (2004), 401--408.Google Scholar
Cross Ref
- G. Erkan and D. R. Radev. 2004. LexRank: Graph-based lexical centrality as salience in text summarization. J. Artif. Intell. Res. 22, 1 (2004), 457--479.Google Scholar
Digital Library
- H. Lin and J. Bilmes. 2010. Multi-document summarization via budgeted maximization of submodular functions. In Proceedings of Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL’10), 912--920.Google Scholar
- K. Riedhammer, B. Favrec, and D. Hakkani-Tür. 2010. Long story short - Global unsupervised models for keyphrase based meeting summarization. Speech Commun. 52, 10 (2010), 801--815.Google Scholar
Digital Library
- M. A. Fattah and F. Ren. 2009. GA, MR, FFNN, PNN and GMM based models for automatic text summarization. Comput. Speech Lang. 23, 1 (2009), 126--144.Google Scholar
Digital Library
- J. Kupie, J. Pedersen, and F. Chen. 1995. A trainable document summarizer. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’95), 68--73.Google Scholar
- J. Zhang and P. Fung. 2007. Speech summarization without lexical features for Mandarin broadcast news. In Proceedings of the Annual Conference of the North AMERICAN Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL’07), 213--216.Google Scholar
- M. Galley. 2006. Skip-chain conditional random field for ranking meeting utterances by importance. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’06), 364--372.Google Scholar
Cross Ref
- R. Baeza-Yates and B. Ribeiro-Neto. 2011. Modern Information Retrieval: The Concepts and Technology behind Search. ACM Press.Google Scholar
- C.-X. Zhai. 2008. Statistical language models for information retrieval: A critical review. Found. Trends Inf. Retriev. 2, 3 (2008), 137--213.Google Scholar
Digital Library
- Y. Lv and C.-X. Zhai. 2015. Negative query generation: Bridging the gap between query likelihood retrieval models and relevance. Inf. Retriev. J. 18, 4 (2015), 359--378.Google Scholar
Digital Library
- R. Rahimi, A. Shakery, and I. King. 2016. Extracting translations from comparable corpora for Cross-Language Information Retrieval using the language modeling framework. Inf. Process. Manage. 52, 2 (2016), 299--318.Google Scholar
Digital Library
- S. Liang and M. Rijke. 2016. Formal language models for finding groups of experts. Inf. Process. Manage. 52, 4 (2016), 529--549.Google Scholar
Digital Library
- A. Haghighi and L. Vanderwende. 2009. Exploring content models for multi-document summarization. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT’09), 362--370.Google Scholar
- S.-H. Liu, K.-Y. Chen, Y.-L. Hsieh, B. Chen, H.-M. Wang, H.-C. Yen, and W.-L. Hsu. 2014. Enhanced language modeling for extractive speech summarization with sentence relatedness information. In Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech’14), 1865--1869.Google Scholar
- S.-H Liu, K.-Y. Chen, Y.-L. Hsieh, B. Chen, H.-M. Wang, H.-C. Yen, and W.-L. Hsu. 2017. A position-aware language modeling framework for extractive broadcast news speech summarization, ACM Trans. Asian Low-Res. Lang. Inf. Process. 16, 4 (2017), 27:1--27:13.Google Scholar
- C.-X. Zhai and J. Lafferty. 2001. Model-based feedback in the language modeling approach to information retrieval. In Proceedings of Conference on Information and Knowledge Management (CIKM’01), 403--410.Google Scholar
- V. Lavrenko and B. Croft. 2001. Relevance-based language models. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’01), 120--127.Google Scholar
- B. Chen and K.-Y. Chen. 2013. Leveraging relevance cues for language modeling in speech recognition. Inf. Process. Manage. 49, 4 (2013), 807--816.Google Scholar
Digital Library
- J. Frederick. 1999. Statistical Methods for Speech Recognition. The MIT Press.Google Scholar
- R. A. A. K. Lund and C. Burgess. 1995. Semantic and associative priming in high-dimensional semantic space. In Proceedings of the Annual Conference of the Cognitive Science Society, 660--665.Google Scholar
- J. Miao, J. X. Huang, and Z. Ye. 2012. Proximity-based Rocchio's model for pseudo relevance feedback. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’12), 535--544.Google Scholar
- D. Metzler and W. B. Croft. 2005. A markov random field model for term dependencies. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’05), 472--479.Google Scholar
- Y. Lv and C.-X. Zhai. 2010. Positional relevance model for pseudo relevance feedback. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’10), 579--586.Google Scholar
Digital Library
- X. Liu and W. B. Croft. 2004. Cluster-based retrieval using language models. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’04), 186--193.Google Scholar
- Y. Huang, L. Sun and J. Y. Nie. 2009. Smoothing document language model with local word graph. In Proceedings of the ACM Conference on Information and Knowledge Management (CIKM’09), 1943--1946.Google Scholar
- K. S. Lee and W. B. Croft 2013. A deterministic resampling method using overlapping document clusters for pseudo-relevance feedback. Inf. Process. Manage. 49, 4 (2013), 792--806.Google Scholar
Digital Library
- H.-M. Wang, B. Chen, J.-W. Kuo, and S.-S. Cheng. 2005. MATBN: A Mandarin Chinese broadcast news corpus. Int. J. Comput. Linguist Chin. Lang. Process. 10, 2 (2005), 219--236.Google Scholar
- J.-T. Chien. (2015). Hierarchical Pitman-Yor-Dirichlet language model. IEEE/ACM Trans. Audio Speech Lang. Process. 23, 8 (2015), 1259--1272.Google Scholar
Digital Library
- C.-L Huang and C.-H. Wu. 2007. Spoken document retrieval using multi-level knowledge and semantic verification. IEEE Trans. Audio Speech Lang. Process. 15, 8 (2007), 2551--2560.Google Scholar
Digital Library
- C.-Y. Lin. 2003. ROUGE: Recall-oriented understudy for gisting evaluation. Retrieved from http://haydn.isi.edu/ROUGE/.Google Scholar
- B. Chen, J.-W. Kuo, and W.-H. Tsai. 2004. Lightly supervised and data-driven approaches to Mandarin broadcast news transcription. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’04), 777--780.Google Scholar
- B. Chen, S.-H. Lin, Y.-M. Chang, and J.-W. Liu. 2013. Extractive speech summarization using evaluation metric-related training criteria. Inf. Process. Manage. 49, 1 (2013), 1--12.Google Scholar
Digital Library
- J. Pennington, R. Socher, and C. D. Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14), 1532--1543.Google Scholar
- Q. Le and T. Mikolov. 2014. Distributed representations of sentences and documents. In Proceedings of the 31st International Conference on International Conference on Machine Learning (ICML’14), 1188--1196.Google Scholar
- M. Sundermeyer, H. Ney, and R. Schluter. 2015. From feedforward to recurrent LSTM neural networks for language modeling. IEEE/ACM Trans. Audio Speech Lang. Process. 23, 3 (2015), 517--529.Google Scholar
Digital Library
- H. Palangi, L. Deng, Y. Shen, J. Gao, X. He, J. Chen, X. Song, and R. Ward. 2016. Deep sentence embedding using the long short term memory network: Analysis and application to information retrieval. IEEE/ACM Trans. Audio Speech Lang. Process. 24, 4 (2016), 694--707.Google Scholar
Digital Library
- K.-Y. Chen, S.-H. Liu, B. Chen, H.-M. Wang, E.-E. Jan, W.-L. Hsu, and H.-H. Chen. 2015. Extractive broadcast news summarization leveraging recurrent neural network language modeling techniques. IEEE/ACM Trans. Audio Speech Lang. Process. 23, 8 (2015), 1322--1334.Google Scholar
Digital Library
- S. Yan and X. Wan. 2014. SRRank: Leveraging semantic roles for extractive multi-document summarization. IEEE/ACM Trans. Audio Speech Lang. Process. 22, 12 (2014), 2048--2058.Google Scholar
Digital Library
- X. Wang, Y. Yoshida, T. Hirao, K. Sudoh, and M. Nagata. 2015. Summarization based on task-oriented discourse parsing. IEEE/ACM Trans. Audio Speech Lang. Process. 23, 8 (2015), 1358--1367.Google Scholar
Digital Library
- G. Shang, W. Ding, Z. Zhang, A. J.-P. Tixier, P. Meladianos, M. Vazirgiannis, and J.-P. Lorré. 2018. Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL’18), 664--674.Google Scholar
Cross Ref
- T. Hasan, M. Abdelwahab, S. Parthasarathy, C. Busso, and Y. Liu. 2016. Automatic composition of broadcast news summaries using rank classifiers trained with acoustic and lexical features. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’16), 6080--6084.Google Scholar
- C.-I Tsai, H.-T. Hung, K.-Y. Chen, and B. Chen. 2016. Extractive speech summarization leveraging convolutional neural network techniques. In Proceedings of the IEEE Workshop on Spoken Language Technology (SLT’16), 158--164Google Scholar
- G. Murray, S. Renals, J. Carletta, and J. Moore. 2005. Evaluating automatic summaries of meeting recordings. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, 33--40.Google Scholar
- Z. Cao, F. Wei, S. Li, W. Li, M. Zhou, and H. Wang. 2015. Learning summary prior representation for extractive summarization. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 829--833.Google Scholar
- T. Tao and C.-X. Zhai. 2006. Regularized estimation of mixture models for robust pseudo-relevance feedback. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’06). 162--169Google Scholar
Digital Library
- T.-E. Liu, S.-H. Liu, and B. Chen. 2019. A hierarchical neural summarization framework for spoken documents. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’19).Google Scholar
- J. Clarke and M. Lapata. 2010. Discourse constraints for document compression. J. Mach. Learn. Res. 36, 3, 411--441.Google Scholar
- S. Narayan, S. B. Cohen, and M. Lapata. 2018. Ranking sentences for extractive summarization with reinforcement learning. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT’18). 1747--1759.Google Scholar
Index Terms
Enhanced Language Modeling with Proximity and Sentence Relatedness Information for Extractive Broadcast News Summarization
Recommendations
A Position-Aware Language Modeling Framework for Extractive Broadcast News Speech Summarization
Extractive summarization, a process that automatically picks exemplary sentences from a text (or spoken) document with the goal of concisely conveying key information therein, has seen a surge of attention from scholars and practitioners recently. Using ...
Sentence Relations for Extractive Summarization with Deep Neural Networks
Sentence regression is a type of extractive summarization that achieves state-of-the-art performance and is commonly used in practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to ...
Extractive text summarization using clustering-based topic modeling
AbstractText summarization is the process of converting the input document into a short form, provided that it preserves the overall meaning associated with it. Primarily, text summarization is achieved in two ways, i.e., abstractive and extractive. ...






Comments