CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions
4665Authors
nan
Abstract
AbstractStory generation has emerged as an interesting yet challenging NLP task in recent years. Some existing studies aim at generating fluent and coherent stories from keywords and outlines; while others attempt to control the global features of the story, such as emotion, style and topic. However, these works focus on coarse-grained control on the story, neglecting control on the details of the story, which is also crucial for the task. To fill the gap, this paper proposes a model for fine-grained control on the story, which allows the generation of customized stories with characters, corresponding actions and emotions arbitrarily assigned. Extensive experimental results on both automatic and human manual evaluations show the superiority of our method. It has strong controllability to generate stories according to the fine-grained personalized guidance, unveiling the effectiveness of our methodology. Our code is available at https://github.com/victorup/CHAE.
Keywords
Full Content
Proceedings of the 29th International Conference on Computational Linguistics, pages 660–668 October 12–17, 2022. 660 Target-Guided Open-Domain Conversation Planning Yosuke Kishinami1 Reina Akama1,2 Shiki Sato1 Ryoko Tokuhisa1 Jun Suzuki1,2 Kentaro Inui1,2 1Tohoku University 2RIKEN yosuke.kishinami.q8@dc.tohoku.ac.jp {akama,shiki.sato.d1,tokuhisa,jun.suzuki,inui}@tohoku.ac.jp Abstract Prior studies addressing target-oriented con- versational tasks lack a crucial notion that has been intensively studied in the context of goal- oriented artificial intelligence agents, namely, planning. In this study, we propose the task of Target-Guided Open-Domain Conversation Planning (TGCP) task to evaluate whether neu- ral conversational agents have goal-oriented conversation planning abilities. Using the TGCP task, we investigate the conversation planning abilities of existing retrieval models and recent strong generative models. The ex- perimental results reveal the challenges facing current technology. 1 Introduction Neural conversational agents have achieved great successes in recent years, and various methods have been proposed to generate informative responses, e.g., the use of knowledge (Zhao et al., 2020; Wu et al., 2020), personality (Li et al., 2016; Zhang et al., 2018), emotional considerations (Rashkin et al., 2019; Zhong et al., 2020), and large-scale models (Zhang et al., 2020; Adiwardana et al., 2020; Roller et al., 2021; Thoppilan et al., 2022). One hot topic in this research area is to develop proactive behavior in agents. For example, Tang et al. (2019) proposed the task of Target-Guided Open-Domain Conversation, in which an agent is required to actively lead a conversation to a pre- defined target word. Wu et al. (2019) proposed a task that uses a knowledge graph to actively lead a conversation to a target entity. Several studies have implemented these target-oriented task set- tings (Dai et al., 2019; Qin et al., 2020; Yuan and An, 2020; Zhong et al., 2021; Zhu et al., 2021). However, these prior studies all lack planning, a crucial notion that has been intensively studied in the context of goal-oriented artificial intelligence (AI) agents (Norvig and Russell, 1995; Kuijpers and Dockx, 1998; Stent et al., 2004; Walker et al., 𝑢!: Hi, What do you do for living? 𝑔!: book 𝑢": I work as an engineer. 𝑢#: That sounds nice. How do you learn coding? Conversational agent 𝑢$: I read and learn from technical books. ( Target word ) Input Output (Initial utterance and target word) (Conversation plan) Figure 1: Overview of the TGCP task. 2007, etc.) and has also been introduced in neu- ral conversational agents (Botea et al., 2019; Jiang et al., 2019a,b). In other words, these studies do not explicitly consider the generation of a multiple-step plan to achieve a target. Given this background, in this study, we propose the Target-Guided Open-Domain Conversation Planning (henceforth, TGCP) task such that an agent’s planning ability in goal-oriented conversa- tions can be assessed. The TGCP task is to produce a plan that leads a conversation to a given target, as illustrated in Figure 1. The point is to consider the task of producing a conversation plan for sev- eral utterances ahead, which we first address in the aforementioned context of Target-Guided Open- Domain Conversation. Furthermore, …
Content truncated to 500 words
Labeled Text
AbstractStory generation has emerged as an interesting yet challenging NLP task in recent years. Some existing studies aim at generating fluent and coherent stories from keywords and outlines; while others attempt to control the global features of the story, such as emotion, style and topic. However, these works focus on coarse-grained control on the story, neglecting control on the details of the story, which is also crucial for the task. To fill the gap, this paper proposes a model for fine-grained control on the story, which allows the generation of customized stories with characters, corresponding actions and emotions arbitrarily assigned. Extensive experimental results on both automatic and human manual evaluations show the superiority of our method. It has strong controllability to generate stories according to the fine-grained personalized guidance, unveiling the effectiveness of our methodology. Our code is available at
Publication Details
- Paper ID:
- 4665
- Year:
- 2022
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan