Abstract
Multi-document summarization (MDS) is an important branch of information aggregation. Compared with the single-document summary (SDS), MDS faces the problem of large search space, redundancy and complex cross-document relation. In this paper, we propose an abstractive MDS model based on Transformer, which considers the parallel information of documents with the graph attention network. During decoding, our model can utilize graph information to guide the summary generation. In addition, combined with the pre-trained language model, our model can further improve the summarization performance. Empirical results on the Multi-News and WikiSum datasets show that our model brings substantial improvements over several strong baselines, and ablation studies verify the effectiveness of our key mechanisms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Liu, Y., Lapata, M.: Hierarchical transformers for multi-document summarization. arXiv preprint arXiv:1905.13164 (2019)
Li, W., Xiao, X., Liu, J., Wu, H., Wang, H., Du, J.: Leveraging graph to improve abstractive multi-document summarization. arXiv preprint arXiv:2005.10043 (2020)
Fabbri, A.R., Li, I., She, T., Li, S., Radev, D.R.: Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model. arXiv preprint arXiv:1906.01749 (2019)
Radev, D.: A common theory of information fusion from multiple text sources step one: cross-document structure. In: 1st SIGdial Workshop on Discourse and Dialogue, pp. 74–83 (2000)
Zhou, H., Ren, W., Liu, G., Su, B., Lu, W.: Entity-aware abstractive multi-document summarization. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 351–362 (2021)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
Banerjee, S., Mitra, P., Sugiyama, K.: Multi-document abstractive summarization using ILP based multi-sentence compression. In: Twenty-Fourth International Joint Conference on Artificial Intelligence (2015)
Li, W., Zhuge, H.: Abstractive multi-document summarization based on semantic link network. In: IEEE Transactions on Knowledge and Data Engineering (2019)
Bing, L., Li, P., Liao, Y., Lam, W., Guo, W., Passonneau, R.J.: Abstractive multi-document summarization via phrase selection and merging. arXiv preprint arXiv:1506.01597 (2015)
Chu, E., Liu, P.: Meansum: a neural model for unsupervised multi-document abstractive summarization. In: International Conference on Machine Learning, pp. 1223–1232. PMLR (2019)
Zhang, J., Tan, J., Wan, X.: Adapting neural single-document summarization model for abstractive multi-document summarization: a pilot study. In: Proceedings of the 11th International Conference on Natural Language Generation, pp. 381–390 (2018)
Lebanoff, L., Song, K., Liu, F.: Adapting the neural encoder-decoder framework from single to multi-document summarization. arXiv preprint arXiv:1808.06218 (2018)
Pasunuru, R., et al.: Data augmentation for abstractive query-focused multi-document summarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 13666–13674 (2021)
Lebanoff, L., Wang, B., Feng, Z., Liu, F.: Modeling endorsement for multi-document abstractive summarization. In: Proceedings of the Third Workshop on New Frontiers in Summarization, pp. 119–130 (2021)
Erkan, G., Radev, D.R.: LexRank: graph-based lexical centrality as salience in text summarization. J. Artif. Intell. Res. 22, 457–479 (2004)
Mihalcea, R., Tarau, P.: TextRank: bringing order into text. In: Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pp. 404–411 (2004)
Wan, X.: An exploration of document impact on graph-based multi-document summarization. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp. 755–762 (2008)
Tan, J., Wan, X., Xiao, J.: Abstractive document summarization with a graph-based attentional neural model. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1171–1181 (2017)
Huang, L., Wu, L., Wang, L.: Knowledge graph-augmented abstractive summarization with semantic-driven cloze reward. arXiv preprint arXiv:2005.01159 (2020)
Christensen, J., Soderland, S., Etzioni, O., et al.: Towards coherent multi-document summarization. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1163–1173 (2013)
Fan, A., Gardent, C., Braud, C., Bordes, A.: Using local knowledge graph construction to scale seq2seq models to multi-document inputs. arXiv preprint arXiv:1910.08435 (2019)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
Wang, D., Liu, P., Zheng, Y., Qiu, X., Huang, X.J.: Heterogeneous graph neural networks for extractive document summarization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6209–6219 (2020)
See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368 (2017)
Liu, P.J., et al.: Generating wikipedia by summarizing long sequences. arXiv preprint arXiv:1801.10198 (2018)
Gehrmann, S., Deng, Y., Rush, A.M.: Bottom-up abstractive summarization. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4098–4109 (2018)
Acknowledgments
This research work has been funded by the National Natural Science Foundation of China (Grant No. U21B2020).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, M., Liang, L., Liu, G. (2022). Parallel Relationship Graph to Improve Multi-Document Summarization. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13530. Springer, Cham. https://doi.org/10.1007/978-3-031-15931-2_52
Download citation
DOI: https://doi.org/10.1007/978-3-031-15931-2_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15930-5
Online ISBN: 978-3-031-15931-2
eBook Packages: Computer ScienceComputer Science (R0)