Learning to Write with Cooperative Discriminators

Holtzman, Ari; Buys, Jan; Forbes, Maxwell; Bosselut, Antoine; Golub, David; Choi, Yejin

doi:10.18653/v1/p18-1152

Cited by 316 publications

(398 citation statements)

References 37 publications

Supporting

Mentioning

261

Contrasting

Unclassified

Order By: Relevance

“…In neural text generation, it is less easy to impose a narrative structure on the generated texts -unless the task is split into two steps, like in the work of Yao et al (2019). An alternative way improve the global coherence in texts generated with recurring neural networks was proposed by Holtzman et al (2018), who used a set of discriminators to encode various aspects of proper writing.…”

Section: Narrative Coherencementioning

confidence: 99%

Narrative Generation in the Wild: Methods from NaNoGenMo

Stegeren¹,

Theune²

2019

Proceedings of the Second Workshop on Storytelling

View full text Add to dashboard Cite

In text generation, generating long stories is still a challenge. Coherence tends to decrease rapidly as the output length increases. Especially for generated stories, coherence of the narrative is an important quality aspect of the output text. In this paper we examine how narrative coherence is attained in the submissions of NaNoGenMo 2018, an online text generation event where participants are challenged to generate a 50,000 word novel. We list the main approaches that were used to generate coherent narratives and link them to scientific literature. Finally, we give recommendations on when to use which approach.

show abstract

Section: Narrative Coherencementioning

confidence: 99%

Narrative Generation in the Wild: Methods from NaNoGenMo

Stegeren¹,

Theune²

2019

Proceedings of the Second Workshop on Storytelling

View full text Add to dashboard Cite

show abstract

“…BookCorpus BookCorpus is a set of unpublished novels (Romance, Fantasy, Science fiction, and Teen genres) collected by Zhu et al (2015). We use a publicly available pre-trained BookCorpus language model from Holtzman et al (2018).…”

Section: Training Datamentioning

confidence: 99%

Learning to Explain: Answering Why-Questions via Rephrasing

Nie¹,

Bennett²,

Goodman³

2019

Proceedings of the First Workshop on NLP for Conversational AI

View full text Add to dashboard Cite

Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning. Previous work has either relied on human-curated structured knowledge bases or detailed domain representation to generate satisfactory explanations. They are also often limited to ranking pre-existing explanation choices. In our work, we contribute to the under-explored area of generating natural language explanations for general phenomena. We automatically collect large datasets of explanation-phenomenon pairs which allow us to train sequence-to-sequence models to generate natural language explanations. We compare different training strategies and evaluate their performance using both automatic scores and human ratings. We demonstrate that our strategy is sufficient to generate highly plausible explanations for general open-domain phenomena compared to other models trained on different datasets.

show abstract

“…In neural text generation, it is less easy to impose a narrative structure on the generated texts -unless the task is split into two steps, like in the work of . An alternative way improve the global coherence in texts generated with recurring neural networks was proposed by Holtzman et al (2018), who used a set of discriminators to encode various aspects of proper writing.…”

Section: Narrative Coherencementioning

confidence: 99%

Proceedings of the Second Workshop on Storytelling

Ferraro¹,

Huang²,

Lukin³

2019

View full text Add to dashboard Cite

Pictures can enrich storytelling experiences. We propose a framework that can automatically compose a picture book by understanding story text and visualizing it with painting elements, i.e., characters and backgrounds. For story understanding, we extract key information from a story on both sentence level and paragraph level, including characters, scenes and actions. These concepts are organized and visualized in a way that depicts the development of a story. We collect a set of Chinese stories for children and apply our approach to compose pictures for stories. Extensive experiments are conducted towards story event extraction for visualization to demonstrate the effectiveness of our method.

show abstract

Learning to Write with Cooperative Discriminators

Cited by 316 publications

References 37 publications

Narrative Generation in the Wild: Methods from NaNoGenMo

Narrative Generation in the Wild: Methods from NaNoGenMo

Learning to Explain: Answering Why-Questions via Rephrasing

Proceedings of the Second Workshop on Storytelling

Contact Info

Product

Resources

About