WriterForcing: Generating more interesting story endings

Gupta, Prakhar; Kumar, Vinayshekhar Bannihatti; Bhutani, Mukul; Black, Alan W.

doi:10.48550/arxiv.1907.08259

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the various attempts of language generation, story generation has been one of the most popular. In [18], the authors generated interesting and more diverse story endings by training models to emphasize on specific keywords and generate non-generic phrases. Luo et.al incorporated sentiment analysis into story generation by implementing a sentimental analyser and a sentimental generator [25].…”

Section: Language Generationmentioning

confidence: 99%

CreativeBot: a Creative Storyteller Agent Developed by Leveraging Pre-trained Language Models

Elgarf

Peters

2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

In an attempt to nurture children's creativity, we developed a creative conversational agent to be used in a collaborative storytelling context with a child. We presented a novel approach to develop creative AI. Our approach uses the four creativity measures: fluency, flexibility, elaboration and originality in order to generate creative behavior. We analyzed and annotated our previously collected storytelling data sets -collected with children-according to our four creativity measures. We then used the extracted and annotated data (636 statements) in order to fine-tune two pre-trained language models (Open AI GPT-3). The two models were aimed at generating creative versus non-creative behavior in a collaborative storytelling scenario. We developed the two models to be able to assess the results and compare them together. We conducted an evaluation to assess stories generated collaboratively between a human and both agents separately (n = 26). Adult Users rated the creativity of the agent according to the stories generated. Results showed that the creative agent was perceived as significantly more creative than the non-creative agent. With the experiment results confirming the validity of our system, we may therefore proceed with testing the effects of the creative behavior of the agent on children's creativity skills.

show abstract

Section: Language Generationmentioning

confidence: 99%

CreativeBot: a Creative Storyteller Agent Developed by Leveraging Pre-trained Language Models

Elgarf

Peters

2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…Previous works (Li, Ding, and Liu 2018;Gupta et al 2019) are mainly based on Sequence-to-Sequence (Seq2Seq) model (Luong, Pham, and Manning 2015). Because of generating a sentence at a stroke in a left-to-right manner and training with Maximum Likelihood Estimate, they suffer from a well known issue of generating noncoherent and generic plots.…”

Section: Introductionmentioning

confidence: 99%

Story Ending Generation with Multi-Level Graph Convolutional Networks over Dependency Trees

Huang

et al. 2021

AAAI

View full text Add to dashboard Cite

As an interesting and challenging task, story ending generation aims at generating a reasonable and coherent ending for a given story context. The key challenge of the task is to comprehend the context sufficiently and capture the hidden logic information effectively, which has not been well explored by most existing generative models. To tackle this issue, we propose a context-aware Multi-level Graph Convolutional Networks over Dependency Parse (MGCN-DP) trees to capture dependency relations and context clues more effectively. We utilize dependency parse trees to facilitate capturing relations and events in the context implicitly, and Multi-level Graph Convolutional Networks to update and deliver the representation crossing levels to obtain richer contextual information. Both automatic and manual evaluations show that our MGCN-DP can achieve comparable performance with state-of-the-art models. Our source code is available at https://github.com/VISLANG-Lab/MLGCN-DP.

show abstract

“…ACAT (Assistive Context Aware Toolkit) (Nachman, Prasad et al 2018) project is an open source platform developed at Intel Labs to enable people with motor neuron diseases to have full access to the capabilities and applications of their computers using very limited user input (e.g. gaze, single muscle movement, facial gesture, etc).…”

Section: Introductionmentioning

confidence: 99%

“…Response Generator is displayed twice, since it is called twice. loss functions (See et al 2019;Gupta et al 2019), ranking responses (Gao et al 2020), etc. Very few methods today apply online learning approaches to train these generative models(yang Wu, Li, and Yu 2020).…”

Section: Introductionmentioning

confidence: 99%

ACAT-G: An Interactive Learning Framework for Assisted Response Generation

Sahay

et al. 2021

AAAI

View full text Add to dashboard Cite

In this paper, we introduce ACAT-G, an interactive dialogue learning framework that incorporates constant human feedback into fine-tuning language models in order to assist conditioned dialog generation. The system takes in a limited amount of input from a human and generates personalized response corresponding to the context of the conversation within natural dialog time-frame. By combining inspirations from online learning, reinforcement learning, and large scale language models, we expect this project to provide a foundation for human-in-the-loop conditional dialog generation tasks.

show abstract

WriterForcing: Generating more interesting story endings

Cited by 3 publications

References 0 publications

CreativeBot: a Creative Storyteller Agent Developed by Leveraging Pre-trained Language Models

CreativeBot: a Creative Storyteller Agent Developed by Leveraging Pre-trained Language Models

Story Ending Generation with Multi-Level Graph Convolutional Networks over Dependency Trees

ACAT-G: An Interactive Learning Framework for Assisted Response Generation

Contact Info

Product

Resources

About