paper-with-me

홈 › Papers

Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning

2021-12-16 · Amal Alabdulkarim, Winston Li, Lara J. Martin, Mark O. Riedl

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.

📄 PDF Abstract BibTeX arXiv:2112.08593

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningGraph AttentionLanguage ModelingLanguage Modellingreinforcement-learningReinforcement Learning (RL)Story Generation

Similar Papers 제목 키워드 기반

Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Rewards for Goal-directed Molecular Generation

2024-03-29 · Jinyeong Park, Jaegyoon Ahn, Jonghwan Choi, Jibum Kim

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 Learning

Automated Story Generation as Question-Answering

2021-12-07 · Louis Castricato, Spencer Frazier, Jonathan Balloch, Nitya Tarakad 외

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+1

Generating Realistic Stock Market Order Streams

2020-06-07 · ICLR 2019 5 · Junyi Li, Xitong Wang, Yaoyang Lin, Arunesh Sinha 외

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

2019-09-30 · Ana Valeria Gonzalez, Isabelle Augenstein, Anders Søgaard

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 GenerationRetrieval

Vidmento: Creating Video Stories Through Context-Aware Expansion With Generative Video

2026-01-29 · Catherine Yeh, Anh Truong, Mira Dontcheva, Bryan Wang arxiv

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…