Quality Signals in Generated Stories
| Autor: | Manasvi Sagarkar, Kevin Gimpel, John Wieting, Lifu Tu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
business.industry
Computer science media_common.quotation_subject 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Partial evaluation Task (project management) Continuation 0202 electrical engineering electronic engineering information engineering Feature (machine learning) Reinforcement learning 020201 artificial intelligence & image processing Quality (business) Artificial intelligence business Function (engineering) computer Natural language processing Sentence 0105 earth and related environmental sciences media_common |
| Zdroj: | SEM@NAACL-HLT |
| DOI: | 10.18653/v1/s18-2024 |
| Popis: | We study the problem of measuring the quality of automatically-generated stories. We focus on the setting in which a few sentences of a story are provided and the task is to generate the next sentence (“continuation”) in the story. We seek to identify what makes a story continuation interesting, relevant, and have high overall quality. We crowdsource annotations along these three criteria for the outputs of story continuation systems, design features, and train models to predict the annotations. Our trained scorer can be used as a rich feature function for story generation, a reward function for systems that use reinforcement learning to learn to generate stories, and as a partial evaluation metric for story generation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|