Learning to Control the Fine-grained Sentiment for Story Ending Generation

By Fuli Luo, Damai Dai, Pengcheng Yang, Tianyu Liu, Baobao Chang, Zhifang Sui, Xu Sun. 2019

54 citations recorded by the source corpus.

Automatic story ending generation is an interesting and challenging task in natural language generation. Previous studies are mainly limited to generate coherent, reasonable and diversified story endings, and few works focus on controlling the sentiment of story endings. This paper focuses on generating a story ending which meets the given fine-grained sentiment intensity. There are two major challenges to this task. First is the lack of story corpus which has fine-grained sentiment labels. Second is the difficulty of explicitly controlling sentiment intensity when generating endings. Therefore, we propose a generic and novel framework which consists of a sentiment analyzer and a sentimental generator, respectively addressing the two challenges. The sentiment analyzer adopts a series of methods to acquire sentiment intensities of the story dataset. The sentimental generator introduces the sentiment intensity into decoder via a Gaussian Kernel Layer to control the sentiment of the output. To the best of our knowledge, this is the first endeavor to control the fine-grained sentiment for story ending generation without manually annotating sentiment labels. Experiments show that our proposed framework can generate story endings which are not only more coherent and fluent but also able to meet the given sentiment intensity better.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Plug and Play Language Models: A Simple Approach to Controlled Text Generation (2019, neutral): “We explore controlled generation for assistive story writing (Peng et al., 2018; Luo et al., 2019; Yao et al., 2019; Fan et al., 2018).”
Collaborative Storytelling with Large-scale Neural Language Models (2020, methodology): “oach the task by first generating a plot outline and then filling in the language. [Gupta et al. 2019] generate story endings by incorporating keywords and context into a sequence-to-sequence model. [Luo et al. 2019] incorporate sentiment analysis into story ending generation. [See et al. 2019] cond”
Guided Generation of Cause and Effect (2020, background): “Most related is conditional story generation [Guan et al., 2019; Wang and Wan, 2019; Luo et al., 2019; Li et al., 2018b], which aims to generate story continuations based on a given context.”
A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models (2022, unknown): “Storystructure[32,33,40],storyending[85,132], topic[16,73,141,153],persona[15,76] DatatoText Input: [78],genderbias[28,104],subjectivebias[101], socialbias[4,121],sentimentbias[51],toxicity[62,74]) FormatControl Input:DesiredFormat,prompttext Output:Textinpre-definedformation Format[66,70,120,122]…”