Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning
The advent of large pre-trained generative language models has provided a common framework for AI story generation via sampling the model to create sequences that continue the story. However, sampling alone is insufficient for story generation. In particular, it is hard to direct a language model to create stories to reach a specific goal event. We present two automated techniques grounded in deep reinforcement learning and reward shaping to control the plot of computer-generated stories. The first utilizes proximal policy optimization to fine-tune an existing transformer-based language model to generate text continuations but also be goal-seeking. The second extracts a knowledge graph from the unfolding story, which is used by a policy network with graph attention to select a candidate continuation generated by a language model. We report on automated metrics pertaining to how often stories achieve a given goal event as well as human participant rankings of coherence and overall story quality compared to baselines and ablations.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement LearningGraph AttentionLanguage ModelingLanguage Modellingreinforcement-learningReinforcement Learning (RL)Story GenerationSimilar Papers 제목 키워드 기반
Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Rewards for Goal-directed Molecular Generation
Optimizing techniques for discovering molecular structures with desired properties is crucial in artificial intelligence(AI)-based drug discovery. Combining deep generative models with reinforcement learning has emerged …
Drug Discoveryreinforcement-learningReinforcement LearningAutomated Story Generation as Question-Answering
Neural language model-based approaches to automated story generation suffer from two important limitations. First, language model-based story generators generally do not work toward a given goal or ending. Second, they o…
Generative Question AnsweringLanguage ModelingLanguage ModellingQuestion Answering+1Generating Realistic Stock Market Order Streams
We propose an approach to generate realistic and high-fidelity stock market data based on generative adversarial networks (GANs). Our Stock-GAN model employs a conditional Wasserstein GAN to capture history dependence of…
Retrieval-based Goal-Oriented Dialogue Generation
Most research on dialogue has focused either on dialogue generation for openended chit chat or on state tracking for goal-directed dialogue. In this work, we explore a hybrid approach to goal-oriented dialogue generation…
DecoderDialogue GenerationRetrievalVidmento: Creating Video Stories Through Context-Aware Expansion With Generative Video
Video storytelling is often constrained by available material, limiting creative expression and leaving undesired narrative gaps. Generative video offers a new way to address these limitations by augmenting captured medi…