Hafez: an Interactive Poetry Generation System

Ghazvininejad, Marjan; Shi, Xing; Priyadarshi, Jay; Knight, Kevin

doi:10.18653/v1/p17-4008

Cited by 116 publications

(110 citation statements)

References 6 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…By applying deep learning approaches recent years, researches about poetry generation has entered a new stage. Recurrent neural network is widely used to generate poems that can even confuse readers from telling them from poems written by human poets [8,9,12,37,41]. Previous works of poem generation mainly focus on style and rhythmic qualities of poems [12,35], while recent studies introduce topic as a condition for poem generation [8,9,35,41].…”

Section: Related Work 21 Poetry Generationmentioning

confidence: 99%

Beyond Narrative Description

Liu

Katô

et al. 2018

Proceedings of the 26th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Automatic generation of natural language from images has attracted extensive attention. In this paper, we take one step further to investigate generation of poetic language (with multiple lines) to an image for automatic poetry creation. This task involves multiple challenges, including discovering poetic clues from the image (e.g., hope from green), and generating poems to satisfy both relevance to the image and poeticness in language level. To solve the above challenges, we formulate the task of poem generation into two correlated sub-tasks by multi-adversarial training via policy gradient, through which the cross-modal relevance and poetic language style can be ensured. To extract poetic clues from images, we propose to learn a deep coupled visual-poetic embedding, in which the poetic representation from objects, sentiments 1 and scenes in an image can be jointly learned. Two discriminative networks are further introduced to guide the poem generation, including a multi-modal discriminator and a poem-style discriminator. To facilitate the research, we have released two poem datasets by human annotators with two distinct properties: 1) the first human annotated imageto-poem pair dataset (with 8, 292 pairs in total), and 2) to-date the largest public English poem corpus dataset (with 92, 265 different poems in total). Extensive experiments are conducted with 8K images, among which 1.5K image are randomly picked for evaluation. Both objective and subjective evaluations show the superior performances against the state-of-the-art methods for poem generation from images. Turing test carried out with over 500 human subjects, among which 30 evaluators are poetry experts, demonstrates the effectiveness of our approach. * This work was conducted when Bei Liu was a research intern at Microsoft Research. † Corresponding author 1 We consider both adjectives and verbs that can express emotions and feelings as sentiment words in this research.

show abstract

Section: Related Work 21 Poetry Generationmentioning

confidence: 99%

Beyond Narrative Description

Liu

Katô

et al. 2018

Proceedings of the 26th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Despite significant progress in automatic story generation, there has been less emphasis on controllability: having a system takes human inputs and composes stories accordingly. With the recent successes on controllable generation of images (Chen et al, 2016;Siddharth et al, 2017;Lample et al, 2017), dialog responses (Wang et al, 2017), poems (Ghazvininejad et al, 2017), and different styles of text (Hu et al, 2017;Ficler and Goldberg, 2017;Shen et al, 2017;Fu et al, 2017). people would want to control a story generation system to produce interesting and personalized stories.…”

Section: Introductionmentioning

confidence: 99%

Towards Controllable Story Generation

Peng¹,

Ghazvininejad²,

May³

et al. 2018

Proceedings of the First Workshop on Storytelling

Self Cite

124

View full text Add to dashboard Cite

We present a general framework of analyzing existing story corpora to generate controllable and creative new stories. The proposed framework needs little manual annotation to achieve controllable story generation. It creates a new interface for humans to interact with computers to generate personalized stories. We apply the framework to build recurrent neural network (RNN)-based generation models to control story ending valence 1 (Egidi and Gerrig, 2009) and storyline. Experiments show that our methods successfully achieve the control and enhance the coherence of stories through introducing storylines. with additional control factors, the generation model gets lower perplexity, and yields more coherent stories that are faithful to the control factors according to human evaluation.

show abstract

“…With recent work on automatically generating creative language (Ghazvininejad et al, 2017;Stock and Strapparava, 2005;Veale and Hao, 2007, e.g. ), this vision has started to come to fruition.…”

Section: Introductionmentioning

confidence: 99%

Linguistic Features of Helpfulness in Automated Support for Creative Writing

Roemmele¹,

Gordon²

2018

Proceedings of the First Workshop on Storytelling

View full text Add to dashboard Cite

We examine an emerging NLP application that supports creative writing by automatically suggesting continuing sentences in a story. The application tracks users' modifications to generated sentences, which can be used to quantify their "helpfulness" in advancing the story. We explore the task of predicting helpfulness based on automatically detected linguistic features of the suggestions. We illustrate this analysis on a set of user interactions with the application using an initial selection of features relevant to story generation.

show abstract

Hafez: an Interactive Poetry Generation System

Cited by 116 publications

References 6 publications

Beyond Narrative Description

Beyond Narrative Description

Towards Controllable Story Generation

Linguistic Features of Helpfulness in Automated Support for Creative Writing

Contact Info

Product

Resources

About