ScriptWriter: Narrative-Guided Script Generation

37208

Authors

nan

Abstract

AbstractIt is appealing to have a system that generates a story or scripts automatically from a storyline, even though this is still out of our reach. In dialogue systems, it would also be useful to drive dialogues by a dialogue plan. In this paper, we address a key problem involved in these applications - guiding a dialogue by a narrative. The proposed model ScriptWriter selects the best response among the candidates that fit the context as well as the given narrative. It keeps track of what in the narrative has been said and what is to be said. A narrative plays a different role than the context (i.e., previous utterances), which is generally used in current dialogue systems. Due to the unavailability of data for this new application, we construct a new large-scale data collection GraphMovie from a movie website where end- users can upload their narratives freely when watching a movie. Experimental results on the dataset show that our proposed approach based on narratives significantly outperforms the baselines that simply use the narrative as a kind of context.

Keywords

nan

Full Content

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8647–8657 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 8647 ScriptWriter: Narrative-Guided Script Generation Yutao Zhu1, Ruihua Song2,∗, Zhicheng Dou3,∗, Jian-Yun Nie1, Jin Zhou4 1Universit´e de Montr´eal, Montr´eal, Qu´ebec, Canada 2Microsoft XiaoIce, Beijing, China 3Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China 4Beijing Film Academy, Beijing, China yutao.zhu@umontreal.ca, rsong@microsoft.com dou@ruc.edu.cn, nie@iro.umontreal.ca, whitezj@vip.sina.com Abstract It is appealing to have a system that generates a story or scripts automatically from a story- line, even though this is still out of our reach. In dialogue systems, it would also be useful to drive dialogues by a dialogue plan. In this paper, we address a key problem involved in these applications - guiding a dialogue by a narrative. The proposed model ScriptWriter selects the best response among the candidates that fit the context as well as the given narra- tive. It keeps track of what in the narrative has been said and what is to be said. A nar- rative plays a different role than the context (i.e., previous utterances), which is generally used in current dialogue systems. Due to the unavailability of data for this new application, we construct a new large-scale data collection GraphMovie from a movie website where end- users can upload their narratives freely when watching a movie. Experimental results on the dataset show that our proposed approach based on narratives significantly outperforms the baselines that simply use the narrative as a kind of context. 1 Introduction Narrative is generally understood as a way to tell a story. WordNet defines it as “a message that tells the particulars of an act or occurrence or course of events; presented in writing or drama or cinema or as a radio or television program”1. Narrative plays an important role in many natural language process- ing (NLP) tasks. For example, in storytelling, the storyline is a type of narrative, which helps gener- ate coherent and consistent stories (Fan et al., 2018, 2019). In dialogue generation, narrative can be used to define a global plan for the whole conversa- tion session, so as to avoid generating inconsistent ∗Corresponding authors. 1http://wordnetweb.princeton.edu/perl/ webwn?s=narrative Narrative Jenny doesn’t like to go home. To accompany Jenny, Gump decides to go home later. Gump is Jenny’s best friend. 珍妮不喜欢回家。为了陪珍妮,甘决定晚点回家。甘是珍妮最 好的朋友。 Initial line Mama's going to worry about me. 妈会担心我的 1st line Just stay a little longer. 再坐一会! Yeah, and I'll bet you $ 10,000 he laughs his ass off. 我打赌他会笑破肚皮 2nd line Ok, Jenny, I'll stay. 好,珍妮,我留下来 She lived in an old house. 她家的房子破旧 3rd line He was a very loving man. 他是个非常有爱心的人 You are my most special friend. 你是我最特别的朋友 Figure 1: An example of part of a script with a nar- rative extracted from our GraphMovie dataset. The checked lines are from a ground-truth session, while the unchecked responses are other candidates that are relevant but not coherent with the narrative. and scattered responses (Xing et al., 2018; Tian et al., 2017; …

Content truncated to 500 words

Labeled Text

AbstractIt is appealing to have a system that generates a story or scripts automatically from a storyline, even though this is still out of our reach. In dialogue systems, it would also be useful to drive dialogues by a dialogue plan. In this paper, we address a key problem involved in these applications - guiding a dialogue by a narrative. The proposed model ScriptWriter selects the best response among the candidates that fit the context as well as the given narrative. It keeps track of what in the narrative has been said and what is to be said. A narrative plays a different role than the context (i.e., previous utterances), which is generally used in current dialogue systems. Due to the unavailability of data for this new application, we construct a new large-scale data collection GraphMovie from a movie website where end- users can upload their narratives freely when watching a movie. Experimental results on the dataset show that our proposed approach based on narratives significantly outperforms the baselines that simply use the narrative as a kind of context.

Publication Details

Paper ID:
37208
Year:
2020
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan