Filters








114,199 Hits in 5.9 sec

Story Generation from Sequence of Independent Short Descriptions [article]

Parag Jain, Priyanka Agrawal, Abhijit Mishra, Mohak Sukhwani, Anirban Laha, Karthik Sankaranarayanan
2017 arXiv   pre-print
This paper introduces and addresses the task of coherent story generation from independent descriptions, describing a scene or an event.  ...  We then implement a deep recurrent neural network (RNN) architecture that encodes sequence of variable length input descriptions to corresponding latent representations and decodes them to produce well  ...  We introduce the task of generating coherent narratives form a sequence of independent short descriptions, as shown in Figure 1 . e standalone descriptions (in general), although are su ciently informative  ... 
arXiv:1707.05501v2 fatcat:oaa5ficdpvaefoibpeaa63lje4

Contextualize, Show and Tell: A Neural Visual Storyteller [article]

Diana Gonzalez-Rico, Gibran Fuentes-Pineda
2018 arXiv   pre-print
We present a neural model for generating short stories from image sequences, which extends the image description model by Vinyals et al. (Vinyals et al., 2015).  ...  This context vector is used as the first state of multiple independent decoder LSTMs, each of which generates the portion of the story corresponding to each image in the sequence by taking the image embedding  ...  This task is about generating a story from a sequence of images. Figure 1 shows the difference between descriptions of images in isolation and stories for images in sequence.  ... 
arXiv:1806.00738v1 fatcat:ovu5qsuv6jcv5gow4cdlcyttca

Quantitative Characteristics of Human-Written Short Stories as a Metric for Automated Storytelling

Carlos León, Pablo Gervás, Pablo Delatorre, Alan Tapscott
2020 New generation computing  
from them.  ...  The stories were annotated according to features commonly found in existing automatic story generators.  ...  Section "Outputs of Automated Story Generators" applies the same methods to a compilation of outputs from automated story generators of those reviewed in "Relevant insights from existing story generation  ... 
doi:10.1007/s00354-020-00111-1 fatcat:542lpidyuzgz5lky2wkb4vyelm

Dixit: Interactive Visual Storytelling via Term Manipulation

Chao-Chun Hsu, Yu-Hua Chen, Zi-Yuan Chen, Hsin-Yu Lin, Ting-Hao (Kenneth) Huang, Lun-Wei Ku
2019 The World Wide Web Conference on - WWW '19  
Dixit then generates a short story based on these terms.  ...  The user initiates the process by uploading a sequence of photos.  ...  ACKNOWLEDGEMENT This research is partially supported by Ministry of Science and Technology, Taiwan, under Grant no. MOST108-2634-F-001-004-, MOST108-2634-F-002-008-and MOST107-2218-E-002-009-.  ... 
doi:10.1145/3308558.3314131 dblp:conf/www/HsuCCLHK19 fatcat:uosydh5gfbculp45cu3xn73cvm

Plot Analysis for Describing Punch Line Functions in Shinichi Hoshi's Microfiction

Hajime Murai, Marc Herbstritt
2014 Workshop on Computational Models of Narrative  
This paper proposes a method of describing narrative structure, that focuses on the behavior of the characters in the story.  ...  Utilizing these attributes, the plots of shortshort stories by Shinichi Hoshi can be represented formally.  ...  Utilizing these descriptions of behavior attributes, the plots of Shinichi Hoshi's short-short stories can be formally captured.  ... 
doi:10.4230/oasics.cmn.2014.121 dblp:conf/cmn/Murai14 fatcat:mz2qqzcj25exbfwtorum4nvwuy

Referential continuity and the coherence of discourse

Alan Garnham, Jane Oakhill, P.N. Johnson-Laird
1982 Cognition  
Tite descriptive passages had little referential continuity from one sentence to the next, and as expected the effects of randomisation on co.mpre.hensibility and memory were negligible.  ...  Both groups read a series of short stories presented in the same three versions as used in the previous experiment. .As predicted the ameliorating effects on memory of restoring referential cont'inuity  ...  But, the ori@nal stories with their plausible sequences of &vents are also more redundant than the implausible sequences of the revised random versions, and general knowledge can aid the readers to make  ... 
doi:10.1016/0010-0277(82)90003-8 pmid:7198951 fatcat:4fkq4ibn7vezhgy7le34pzu2zm

TopNet: Learning from Neural Topic Model to Generate Long Stories [article]

Yazheng Yang, Boyuan Pan, Deng Cai, Huan Sun
2021 arXiv   pre-print
Different from most text generation tasks, LSG requires to output a long story of rich content based on a much shorter text input, and often suffers from information sparsity.  ...  Long story generation (LSG) is one of the coveted goals in natural language processing.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Office or the  ... 
arXiv:2112.07259v1 fatcat:hzt7v2qmrngqdbqmnuovumgjk4

Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication [article]

Ruize Wang, Zhongyu Wei, Ying Cheng, Piji Li, Haijun Shan, Ji Zhang, Qi Zhang, Xuanjing Huang
2020 arXiv   pre-print
Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically.  ...  Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content.  ...  Acknowledgements This work is partically supported by National Natural Science Foundation of China (No. 71991471), Science and Technology Commission of Shanghai Municipality Grant (No.20dz1200600, No.18DZ1201000  ... 
arXiv:1911.04192v2 fatcat:ihlxe26jorfdxcdovu7uxfjxym

StoryGAN: A Sequential Conditional GAN for Story Visualization [article]

Yitong Li, Zhe Gan, Yelong Shen, Jingjing Liu, Yu Cheng, Yuexin Wu, Lawrence Carin, David Carlson, Jianfeng Gao
2019 arXiv   pre-print
of the generated sequences.  ...  We propose a new task, called Story Visualization. Given a multi-sentence paragraph, the story is visualized by generating a sequence of images, one for each sentence.  ...  Two discriminators at different levels guide the generation process. on a short description.  ... 
arXiv:1812.02784v2 fatcat:jl3vtrrm55afhag5cnzrfinve4

StoryGAN: A Sequential Conditional GAN for Story Visualization

Yitong Li, Zhe Gan, Yelong Shen, Jingjing Liu, Yu Cheng, Yuexin Wu, Lawrence Carin, David Carlson, Jianfeng Gao
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
of the generated sequences.  ...  We propose a new task, called Story Visualization. Given a multi-sentence paragraph, the story is visualized by generating a sequence of images, one for each sentence.  ...  This task is highly related to text-to-image generation [35, 28, 17, 36, 34] , where an image is generated based on a short description.  ... 
doi:10.1109/cvpr.2019.00649 dblp:conf/cvpr/LiGSLCWCCG19 fatcat:m5tbaaj3ordilcvcx26npjemeq

A Hegemonic View on Short Story Aku dan Mereka Berbeda

Evie Shofiyah Usman, Universitas Banten Jaya
2020 Journal of English Language Teaching and Cultural Studies  
Source of data were taken from the short story entitled Aku dan Mereka Berbeda written by Abdul Latief.  ...  The short story also conveys an ideological hegemony of white skin supremacy.  ...  A short story basically demands a clear description. The characters are the center of attention in the story.  ... 
doi:10.48181/jelts.v3i1.9132 fatcat:xui4c7pq6ba6pfrdosffyie4im

IDIC: assembling video sequences from story plans and content annotations

Sack, Davis
1994 Proceedings of IEEE International Conference on Multimedia Computing and Systems MMCS-94  
§ We describe a system, IDIC, which can generate a video sequence according to a story plan by selecting appropriate segments from an archive of annotated video.  ...  and video story generation.  ...  The support of the Laboratory and its sponsors is gratefully acknowledged.  ... 
doi:10.1109/mmcs.1994.292430 dblp:conf/icmcs/SackD94 fatcat:hdk5g5lkzfgzvizcfz7eg6qy7q

Plot Writing From Pre-Trained Language Models [article]

Yiping Jin, Vishakha Kadam, Dittaya Wanvarie
2022 arXiv   pre-print
We propose generating story plots using off-the-shelf PLMs while maintaining the benefit of content planning to generate cohesive and contentful stories.  ...  Trained on large parallel corpora, these models can generate more logical event sequences and thus more contentful stories.  ...  Plan-and-write generates short commonsense stories similar to the ROCStories dataset it is trained on. Thanks to its storyline generation, there is a logical sequence among the sentences.  ... 
arXiv:2206.03021v1 fatcat:wsr2wddbnvebxmkkceolrnnexa

Knowledge-Based Video Question Answering with Unsupervised Scene Descriptions [article]

Noa Garcia, Yuta Nakashima
2020 arXiv   pre-print
In ROLL, each of these tasks is in charge of extracting rich and diverse information by 1) processing scene dialogues, 2) generating unsupervised video scene descriptions, and 3) obtaining external knowledge  ...  from the different sources.  ...  Scene Description Generation Scene descriptions are generated from the video scene graph according to the set of rules in Table 1 in an unsupervised manner.  ... 
arXiv:2007.08751v1 fatcat:q5upzkoounhtdoynk2wffuspka

Shaping Pupils' Spirituality Through Creating Texts (Based On Mother Tongue Textbook Materials For 8th Grade)

Sanoyeva Mutabar, Independent Researcher Of Navoi State Pedagogical Institute, Uzbekistan
2020 The American Journal of Social Science and Education Innovations  
The main purpose of creating texts in mother tongue lessons is to inculcate in the minds of pupils the ideas of national independence - to teach the next generation to be spiritually mature, patriotic,  ...  It is the upbringing of a perfect and virtuous person who is able to preserve his ideals, who has mastered the science of maturity and eloquence.  ...  of the text in the sequence of exercises.  ... 
doi:10.37547/tajssei/volume02issue11-41 fatcat:3rbqglha6va2hckwb4snrmquaq
« Previous Showing results 1 — 15 out of 114,199 results