Abstract
Although neural abstractive summarization models can generate text with significant fluency and coherence, controlling the correctness of facts in generation remains a challenge. Recent work simply classifies factuality into two categories: factual or non-factual, which is coarse-grained and lacks a deep understanding of the linguistic typology of factual errors. In this paper, we present insights into two main and common factual errors (Semantic Frame Errors and Coreference Error) and propose a LASum model to enhance the factuality of abstractive summarization by adversarial fine-grained fact graph. Specifically, we first construct the fine-grained fact graph for the source document and summary to represent facts, respectively, consisting of a dependency channel and coreference channel to address the above two factual errors. And then we enhance the seq2seq model to grasp the internal facts in the fact graph from an intuitive perspective by adversarial learning (GAN). The experimental results show that our model can substantially improve the factuality compared to several strong baselines.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cao, M., Dong, Y., Cheung, J.C.K.: Inspecting the factuality of hallucinated entities in abstractive summarization. arXiv preprint arXiv:2109.09784 (2021)
Cao, Z., Wei, F., Li, W., Li, S.: Faithful to the original: fact aware neural abstractive summarization. In: AAAI, vol. 32 (2018)
Choubey, P.K., Vig, J., Liu, W., Rajani, N.F.: Mofe: Mixture of factual experts for controlling hallucinations in abstractive summarization. arXiv preprint arXiv:2110.07166 (2021)
Dong, L., et al.: Unified language model pre-training for natural language understanding and generation. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Goyal, T., Durrett, G.: Annotating and modeling fine-grained factuality in summarization. In: NAACL 2021, pp. 1449–1462. Online, June 2021
Hermann, K.M., et al.: Teaching machines to read and comprehend. Adv. Neural. Inf. Process. Syst. 28, 1693–1701 (2015)
Kryscinski, W., McCann, B., Xiong, C., Socher, R.: Evaluating the factual consistency of abstractive text summarization. In: EMNLP,D pp. 9332–9346, November 2020
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL, pp. 7871–7880 (2020)
Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning. In: AAAI (2018)
Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches out, pp. 74–81 (2004)
Liu, Y., Lapata, M.: Text summarization with pretrained encoders. In: EMNLP, pp. 3730–3740 (2019)
Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J.R., Bethard, S., McClosky, D.: The stanford corenlp natural language processing toolkit. In: ACL, pp. 55–60 (2014)
Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Paul Smolley, S.: Least squares generative adversarial networks. In: IEEE, pp. 2794–2802 (2017)
Nan, F., et al.: Improving factual consistency of abstractive summarization via question answering. In: ACL, pp. 6881–6894 (2021)
Narayan, S., Cohen, S.B., Lapata, M.: Don’t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization. In: EMNLP, pp. 1797–1807 (2018)
Pagnoni, A., Balachandran, V., Tsvetkov, Y.: Understanding factuality in abstractive summarization with FRANK: a benchmark for factuality metrics. In: NAACL 2021, pp. 4812–4829. Online, June 2021
Zhang, J., Zhao, Y., Saleh, M., Liu, P.: Pegasus: pre-training with extracted gap-sentences for abstractive summarization. In: ICML, pp. 11328–11339. PMLR (2020)
Zhang, L., Kong, F., Zhou, G.: Adversarial learning for discourse rhetorical structure parsing. In: ACL 2021, (Volume 1: Long Papers), pp. 3946–3957 (2021)
Zhu, C., et al.: Enhancing factual consistency of abstractive summarization. In: NAACL 2021, pp. 718–733. Online, June 2021
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
Gao, Z., Jiang, F., Chu, X., Li, P. (2022). Adversarial Fine-Grained Fact Graph for Factuality-Oriented Abstractive Summarization. In: Lu, W., Huang, S., Hong, Y., Zhou, X. (eds) Natural Language Processing and Chinese Computing. NLPCC 2022. Lecture Notes in Computer Science(), vol 13551. Springer, Cham. https://doi.org/10.1007/978-3-031-17120-8_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-17120-8_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17119-2
Online ISBN: 978-3-031-17120-8
eBook Packages: Computer ScienceComputer Science (R0)
