We introduce TVStoryGen, a story generation dataset that requires generating detailed TV show episode recaps from a brief summary and a set of documents describing the characters involved. Unlike other story generation datasets, TVStoryGen contains stories that are authored by professional screen-...
STORYANALOGY: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understandinghttps://arxiv.org/pdf/2310.12874任务是 narratives' analogy identification and generation,结果是创建 STORYANALOGY dataset (24k pairs)、改良 Structure-Mapping Theory 作为 evaluation 标准、SFT FlanT5-xxl ...
AutoML - Automated machine learning. Upload your dataset and will create an AI model that you can use to make predictions. AI Stock Market Trading - Backtest potential investment strategies to see if they are profitable. Impossible Animals Game - Guess the hybrid animal that does not exist. AI...
4. HUSH: A Dataset and Platform for Human-in-the-Loop Story Generation 会议:EMNLP 2020. Long Paper. 作者:Nader Akoury, Shufan Wang, Josh Whiting, Stephen Hood, Nanyun Peng, Mohit Iyyer 链接:https://www.aclweb.org/anthology/2020.emnlp-main.525.pdf 5. Content Planning for Neural Story ...
Story Generation on TVMegaSite test Leaderboard Dataset View BLEUPerplexityROUGE-1ROUGE-2ROUGE-L by DatePerplexityROUGE-1ROUGE-2ROUGE-L Created with Highcharts 9.3.0BLEU(NN) Oracle plot + summary + oracle char. desc.(NN) Oracle plot + summary + oracle char. desc.Other modelsModels with...
This study addresses and explores the individual performances and capabilities of 3 distinct text generation models based on GAN, RNN & LSTM respectively. The project employed three individual models and trained them on the same dataset and the evaluation was conducted using METEOR scores, accuracy, ...
We still haven’t explained some text-generation parameters like top_p. Stick after the end-credits if you’d like to learn about these parameters. Epilogue and End Credits To recap, we took a dataset of movie plots of various genres and fed it to theGPT2LMHeadModelto fine-tune ...
ArXiv-2024 CMDAG: A Chinese Metaphor Dataset with Annotated Grounds as CoT for Boosting Metaphor Generation [paper] [Yujie Shao, Xinrong Yao, Xingwei Qu, Chenghua Lin, Shi Wang, Stephen W. Huang, Ge Zhang, Jie Fu] ArXiv-2023 STONYBOOK: A System and Resource for Large-Scale Analysis of...
We also release StoryStream, a large-scale dataset specifically designed for training and benchmarking multimodal story generation. TODOs Release the StoryStream dataset. Release inference code and model checkpoints. Release training code for instruction tuning. Introduction The introduced SEED-Story, ...
Story Generation on Fandom dev Leaderboard Dataset View by BLEU(NN) Oracle plot + summary + oracle char. desc.(NN) Oracle plot + summary + oracle char. desc.Other modelsModels with highest BLEU18. Sep28.4 Filter: untagged Edit Leaderboard RankModelBLEUPerplexityROUGE-1ROUGE-2ROUGE-LPaper...