Generative artificial intelligence (AI) is being used to generate all kinds of digital data: images, speech, text, and so on. with high fidelity. Within natural language processing, generative AI has many interesting applications such as summarization and story generation. In this article, we focus on generating alternate endings for short stories. Although some work has been done on story generation, to the best of our knowledge, very little work has been done on generating alternate endings. For a more precise ending, a large amount of context needs to be provided making story ending generation a more challenging problem than complete story generation. We propose a complete pipeline consisting of text understanding and text generation modules for generating story endings. Within story understanding modules, we propose and integrate various sub-modules to capture the context of the story. This context is combined with the original story during the training and story generation phase for which a T5 transformer is used. Compared to previous studies, our proposed model reports a higher BLEU value. We also conducted a subjective user study to evaluate the endings generated by our model. Machine-generate endings were given an average score of 3.82 (out of 5) as opposed to 3.86 for human-generated endings.
WaliAAhmadMNaseerA, et al. Stynmedgan: medical images augmentation using a new gan model for improved diagnosis of diseases. J Intel Fuzzy Syst2023: 1–18.
2.
IrtazaMAliAGulzarM, et al. Multi-label classification of lung diseases using deep learning. IEEE Access, 2024.
3.
FawazAAliMBAdanM, et al. A deep learning framework for efficient high-fidelity speech synthesis: styletts. IKSP J Comput Sci Eng2021; 1(1).
4.
MahmoodHIftikharMWaliA, et al. A novel cascaded approach for classification of tuberculosis using cough audio in real-time environment. IEEE Access, 2024.
5.
WaliAShariqRShoaibS, et al. Recent progress in sign language recognition: a review. Mach Vis Appl2023; 34(6): 127.
6.
HamzaHMWaliA.Pakistan sign language recognition: from videos to images. Signal Image Video Proces2025; 19(8): 1–25.
7.
HamzaHMWaliA.Pakistan sign language recognition: leveraging deep learning models with limited dataset. Mach Vis Appl2023; 34(5): 71.
8.
BrophyEWangZSheQ, et al. Generative adversarial networks in time series: a systematic literature review. ACM Comput Surv2023; 55(10): 1–31.
9.
ChaturvediSPengHRothD.Story comprehension for predicting what happens next. In: Proceedings of the 2017 conference on empirical methods in natural language processing, ACL, 2017, pp. 1603–1614.
SwaminathanAGuptaRKZhangH, et al. Keyphrase generation for scientific articles using gans (student abstract). In: Proceedings of the AAAI conference on artificial intelligence, Vol. 34, AAAI2020, pp. 13931–13932.
12.
AnZLiuS.Towards diverse paraphrase generation using multi-class Wasserstein Gan. arXiv preprint 1909.13827, 2019.
13.
KhanMNaseerAWaliA, et al. A roman urdu corpus for sentiment analysis. Comput J2024: bxae052.
14.
ShahzadAWaliA.Computerization of off-topic essay detection: a possibility?Educ Inform Tech2022; 27(4): 5737–5747.
15.
ShahidRWaliABashirM.Next word prediction for urdu language using deep learning models. Comput Speech Lang2024; 87: 101635.
16.
ZhaiFDembergVShkadzkoP, et al. A hybrid model for globally coherent story generation, Proceedings of the Second Workshop on Storytelling. Assoc Comput Ling2019, pp. 34–45.
17.
SmithTCWittenIH.A planning mechanism for generating story text. Literary Linguist Comput1991; 6(2): 119–126.
18.
GrasbonDBraunN.A morphological approach to interactive storytelling. In: Citeseer, Procedings. CAST01, living in mixed realities. Special issue of netzspannung. Org/Journal, the magazine for media production and Inter-media Research, 2001, pp. 337–340.
19.
AlhussainAIAzmiAM.Automatic story generation: a survey of approaches. ACM Comput Surv2021; 54(5): 1–38.
20.
LuoFDaiDYangP, et al. Learning to control the fine-grained sentiment for story ending generation. In: Proceedings of the 57th annual meeting of the association for computational linguistics, 2019, pp. 6020–6026. Association for Computational Linguistics.
21.
ZhaoYLiuLLiuC, et al. From plots to endings: a reinforced pointer generator for story ending generation. In: Natural language processing and chinese computing: 7th CCF international conference, NLPCC 2018, Hohhot, China, 26–30 August 2018, Proceedings, Part I 7, 2018, pp. 51–63. Springer.
22.
LiuDLiJYuMH, et al. A character-centric neural model for automated story generation, 2020.
23.
LiZDingXLiuT.Generating reasonable and diversified story ending using sequence to sequence model with adversarial training. In: Proceedings of the 27th international conference on computational linguistics, 2018, pp. 1033–1043. Association for Computational Linguistics.
24.
MostafazadehNChambersNHeX, 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, 2016, pp. 839–849, San Diego, CA: Association for Computational Linguistics, https://aclanthology.org/N16-1098
MitriM.Story analysis using natural language processing and interactive dashboards. J Comput Inform Syst2022; 62(2): 216–226.
28.
ClarkEJiYSmithNA.Neural text generation in stories using entity representations as context. In: Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: human language technologies, Volume 1 (Long Papers), 2018, pp. 2250–2260. Association for Computational Linguistics.
29.
SeoHJungSJungJ, et al. Controllable text generation using semantic control grammar. IEEE Access2023; 11: 26329–26343.
30.
SharmaRAllenJBakhshandehO, et al. Tackling the story ending biases in the story cloze test. In: Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 2: Short Papers), 2018, pp. 752–757. Association for Computational Linguistics.
31.
SenadeeraDCIveJ. Controlled text generation using t5 based encoder-decoder soft prompt tuning and analysis of the utility of generated text in AI. arXiv preprint 2212.02924, 2022.
32.
MartinLWVanbergG.A robust transformation procedure for interpreting political text. Politic Anal2008; 16(1): 93–100.
33.
PawadeDSakhaparaAJainM, et al. Story scrambler-automatic text generation using word level rnn-lstm. Int J Inform Tech Comput Sci2018; 10(6): 44–53.
34.
JainPAgrawalPMishraA, et al. Story generation from sequence of independent short descriptions. arXiv preprint 1707.05501, 2017.
35.
GuanJHuangFZhaoZ, et al. A knowledge-enhanced pretraining model for commonsense story generation. Trans Assoc Comput Linguist2020; 8: 93–108.
36.
HuangQGanZCelikyilmazA, et al. Hierarchically structured reinforcement learning for topically coherent visual story generation. In: Proceedings of the AAAI conference on artificial intelligence, Vol. 33, 2019, pp. 8465–8472. AAAI.
37.
PapineniKRoukosSWardT, et al. Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics, 2002, pp. 311–318. Association for Computational Linguistics.
38.
HaoCPangLLanY, et al. Sketch and customize: a counterfactual story generator. Proc AAAI Conf Artif Intel2021; 35: 12955–12962.
