Abstract
Text coherence is a fundamental problem in natural language generation and understanding. Organizing sentences into an order that maximizes coherence is known as sentence ordering. This paper is proposing a new approach based on the graph neural network approach to encode a set of sentences and learn orderings of short stories. We propose a new method for constructing sentence-entity graphs of short stories to create the edges between sentences and reduce noise in our graph by replacing the pronouns with their referring entities. We improve the sentence ordering by introducing an aggregation method based on majority voting of state-of-the-art methods and our proposed one. Our approach employs a BERT-based model to learn semantic representations of the sentences. The results demonstrate that the proposed method significantly outperforms existing baselines on a corpus of short stories with a new state-of-the-art performance in terms of Perfect Match Ratio (PMR) and Kendall’s Tau (\(\tau \)) metrics. More precisely, our method increases PMR and \(\tau \) criteria by more than 5% and 4.3%, respectively. These outcomes highlight the benefit of forming the edges between sentences based on their cosine similarity. We also observe that replacing pronouns with their referring entities effectively encodes sentences in sentence-entity graphs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The entity should be common to at least two sentences.
- 2.
The paragraph vector is nonetheless influenced by the permutations of input sentences.
- 3.
We use the Stanford’s tool [25].
- 4.
For example, either \(s_1 s_2\) or \(s_2 s_1\) occurs, and without a doubt, the co-occurrence of these is a vast and impossible contradiction.
- 5.
Suppose the outputs of the three methods for arranging \(sentence_1\) (\(s_1\)) and \(sentence_2\) (\(s_2\)) are: Method 1: \(s_1\) \(s_2\), Method 2: \(s_1\) \(s_2\), and Method 3: \(s_2\) \(s_1\). Therefore, the order \(s_1\) \(s_2\) gets two points and the order \(s_2\) \(s_1\) gets one, so \(s_1\) \(s_2\) applies to the final output.
- 6.
Either of the two pair orderings that have an “or” between them.
- 7.
[10] did not train ATTOrderNet on the ROCStories dataset.
- 8.
Entity nodes are not connected to all nodes.
- 9.
We train SE-Graph on ROCStories since [47] did not.
- 10.
To demonstrate the advantages of the PG’s BERT-based sentence encoder, this component is considered exactly like the sentence encoder of SE-Graph and ATTOrderNet.
- 11.
Entity nodes can only have a link to sentence nodes.
References
Agrawal, H., Chandrasekaran, A., Batra, D., Parikh, D., Bansal, M.: Sort story: sorting jumbled images and captions into stories. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 925–931. Association for Computational Linguistics, Austin (2016). https://doi.org/10.18653/v1/D16-1091
Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077–6086 (2018)
Barzilay, R., Elhadad, N.: Inferring strategies for sentence ordering in multidocument news summarization. J. Artif. Intell. Res. 17, 35–55 (2002)
Barzilay, R., Lapata, M.: Modeling local coherence: an entity-based approach. Comput. Linguist. 34(1), 1–34 (2008)
Barzilay, R., Lee, L.: Catching the drift: probabilistic content models, with applications to generation and summarization. In: Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics: HLT-NAACL 2004, pp. 113–120 (2004)
Beck, D., Haffari, G., Cohn, T.: Graph-to-sequence learning using gated graph neural networks. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 273–283. Association for Computational Linguistics, Melbourne (2018). https://doi.org/10.18653/v1/P18-1026
Chandu, K., Nyberg, E., Black, A.W.: Storyboarding of recipes: grounded contextual generation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6040–6046 (2019)
Chen, X., Qiu, X., Huang, X.: Neural sentence ordering. ar**v preprint ar**v:1607.06952 (2016)
Christensen, J., Soderland, S., Etzioni, O.: 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. Association for Computational Linguistics, Atlanta (2013). https://www.aclweb.org/anthology/N13-1136
Cui, B., Li, Y., Chen, M., Zhang, Z.: Deep attentive sentence ordering network. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4340–4349 (2018)
Elsner, M., Austerweil, J., Charniak, E.: A unified local and global model for discourse coherence. In: Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference, pp. 436–443 (2007)
Fan, A., Lewis, M., Dauphin, Y.: Strategies for structuring story generation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2650–2660. Association for Computational Linguistics, Florence (2019). https://doi.org/10.18653/v1/P19-1254
Galanis, D., Lampouras, G., Androutsopoulos, I.: Extractive multi-document summarization with integer linear programming and support vector regression. In: Proceedings of COLING 2012, pp. 911–926 (2012)
Golestani, M., Razavi, S.Z., Borhanifard, Z., Tahmasebian, F., Faili, H.: Using BERT encoding and sentence-level language model for sentence ordering. In: Ekštein, K., Pártl, F., Konopík, M. (eds.) Text, Speech, and Dialogue, pp. 318–330. Springer International Publishing, Cham (2021)
Gong, J., Chen, X., Qiu, X., Huang, X.: End-to-end neural sentence ordering using pointer network. ar**v preprint ar**v:1611.04953 (2016)
Guinaudeau, C., Strube, M.: Graph-based local coherence modeling. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 93–103 (2013)
Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 1025–1035. NIPS 2017, Curran Associates Inc., Red Hook, NY (2017)
Hu, J., Cheng, Y., Gan, Z., Liu, J., Gao, J., Neubig, G.: What makes a good story? Designing composite rewards for visual storytelling. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7969–7976 (2020)
Johnson, D.: Learning graphical state transitions. In: ICLR (2017)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. ar**v preprint ar**v:1609.02907 (2017)
Konstas, I., Lapata, M.: Concept-to-text generation via discriminative reranking. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 369–378 (2012)
Kumar, P., Brahma, D., Karnick, H., Rai, P.: Deep attentive ranking networks for learning to order sentences. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 8115–8122 (2020)
Lapata, M.: Probabilistic text structuring: experiments with sentence ordering. In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pp. 545–552 (2003)
Lapata, M.: Automatic evaluation of information ordering: Kendall’s tau. Comput. Linguist. 32(4), 471–484 (2006). https://doi.org/10.1162/coli.2006.32.4.471
Lee, H., Peirsman, Y., Chang, A., Chambers, N., Surdeanu, M., Jurafsky, D.: Stanford’s multi-pass sieve coreference resolution system at the CoNLL-2011 shared task. In: Proceedings of the 15th Conference on Computational Natural Language Learning: Shared Task, pp. 28–34. Association for Computational Linguistics (2011)
Li, J., Hovy, E.: A model of coherence based on distributed sentence representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 2039–2048 (2014)
Li, J., Jurafsky, D.: Neural net models of open-domain discourse coherence. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 198–209. Association for Computational Linguistics, Copenhagen (2017). https://doi.org/10.18653/v1/D17-1019
Liu, X., Shen, Y., Duh, K., Gao, J.: Stochastic answer networks for machine reading comprehension. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 1694–1704. Association for Computational Linguistics, Melbourne (2018). https://doi.org/10.18653/v1/P18-1157
Logeswaran, L., Lee, H., Radev, D.: Sentence ordering and coherence modeling using recurrent neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Louis, A., Nenkova, A.: A coherence model based on syntactic patterns. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 1157–1168 (2012)
Marcheggiani, D., Titov, I.: Encoding sentences with graph convolutional networks for semantic role labeling. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1506–1515. Association for Computational Linguistics, Copenhagen (2017). https://doi.org/10.18653/v1/D17-1159
Mostafazadeh, N., et al.: A corpus and cloze evaluation for deeper understanding of commonsense stories. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 839–849. Association for Computational Linguistics, San Diego (2016). https://doi.org/10.18653/v1/N16-1098
Mostafazadeh, N., Roth, M., Louis, A., Chambers, N., Allen, J.: LSDSem 2017 shared task: the story cloze test. In: Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, pp. 46–51. Association for Computational Linguistics, Valencia (2017). https://doi.org/10.18653/v1/W17-0906
Nallapati, R., Zhai, F., Zhou, B.: SummaRuNNer: a recurrent neural network based sequence model for extractive summarization of documents. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)
Pour, M.G., Razavi, S.Z., Faili, H.: A new sentence ordering method using BERT pretrained model. In: 2020 11th International Conference on Information and Knowledge Technology (IKT), pp. 132–138. IEEE (2020)
Prabhumoye, S., Salakhutdinov, R., Black, A.W.: Topological sort for sentence ordering. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2783–2792. Association for Computational Linguistics, Online (2020). https://doi.org/10.18653/v1/2020.acl-main.248
Rahutomo, F., Kitasuka, T., Aritsugi, M.: Semantic cosine similarity. In: The 7th International Student Conference on Advanced Science and Technology ICAST, vol. 4, p. 1 (2012)
Reiter, E., Dale, R.: Building applied natural language generation systems. Nat. Lang. Eng. 3(1), 57–87 (1997)
Song, L., Zhang, Y., Wang, Z., Gildea, D.: N-ary relation extraction using graph-state LSTM. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2226–2235. Association for Computational Linguistics, Brussels (2018). https://doi.org/10.18653/v1/D18-1246
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, vol. 2, pp. 3104–3112. NIPS 2014, MIT Press, Cambridge (2014)
Wang, B., Kuo, C.C.J.: SBERT-WK: a sentence embedding method by dissecting BERT-based word models. IEEE/ACM Trans. Audio Speech Lang. Process. 28, 2146–2157 (2020)
Wang, T., Wan, X.: Hierarchical attention networks for sentence ordering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 7184–7191 (2019)
Wang, Z., Lv, Q., Lan, X., Zhang, Y.: Cross-lingual knowledge graph alignment via graph convolutional networks. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 349–357. Association for Computational Linguistics, Brussels (2018). https://doi.org/10.18653/v1/D18-1032
Yanase, T., et al.: Learning sentence ordering for opinion generation of debate. In: Proceedings of the 2nd Workshop on Argumentation Mining, pp. 94–103 (2015)
Yasunaga, M., Zhang, R., Meelu, K., Pareek, A., Srinivasan, K., Radev, D.: Graph-based neural multi-document summarization. In: Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pp. 452–462. Association for Computational Linguistics, Vancouver (2017). https://doi.org/10.18653/v1/K17-1045
Yin, Y., et al.: Enhancing pointer network for sentence ordering with pairwise ordering predictions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 9482–9489 (2020)
Yin, Y., Song, L., Su, J., Zeng, J., Zhou, C., Luo, J.: Graph-based neural sentence ordering. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, pp. 5387–5393. International Joint Conferences on Artificial Intelligence Organization (2019). https://doi.org/10.24963/ijcai.2019/748
Yu, A.W., et al.: QANet: combining local convolution with global self-attention for reading comprehension. ar**v preprint ar**v:1804.09541 (2018)
Zeng, X., Li, J., Wang, L., Beauchamp, N., Shugars, S., Wong, K.F.: Microblog conversation recommendation via joint modeling of topics and discourse. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long Papers), pp. 375–385 (2018)
Zhang, Y., Liu, Q., Song, L.: Sentence-state LSTM for text representation. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 317–327. Association for Computational Linguistics, Melbourne (2018). https://doi.org/10.18653/v1/P18-1030
Zhu, Y., Song, R., Dou, Z., Nie, J.Y., Zhou, J.: ScriptWriter: narrative-guided script generation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8647–8657. Association for Computational Linguistics, Online (2020). https://doi.org/10.18653/v1/2020.acl-main.765
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
Golestani, M., Borhanifard, Z., Tahmasebian, F., Faili, H. (2022). Pruned Graph Neural Network for Short Story Ordering. In: Bandini, S., Gasparini, F., Mascardi, V., Palmonari, M., Vizzari, G. (eds) AIxIA 2021 – Advances in Artificial Intelligence. AIxIA 2021. Lecture Notes in Computer Science(), vol 13196. Springer, Cham. https://doi.org/10.1007/978-3-031-08421-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-08421-8_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08420-1
Online ISBN: 978-3-031-08421-8
eBook Packages: Computer ScienceComputer Science (R0)