{"title":"使用生成模型和持续行动策略构建叙事","authors":"E. Chourdakis, J. Reiss","doi":"10.18653/v1/W17-3905","DOIUrl":null,"url":null,"abstract":"This paper proposes a method for learning how to generate narrative by recombining sentences from a previous collection. Given a corpus of story events categorised into 9 topics, we approximate a deep reinforcement learning agent policy to recombine them in order to satisfy narrative structure. We also propose an evaluation of such a system. The evaluation is based on coherence, interest, and topic, in order to figure how much sense the generated stories make, how interesting they are, and examine whether new narrative topics can emerge.","PeriodicalId":162824,"journal":{"name":"CC-NLG@INLG","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Constructing narrative using a generative model and continuous action policies\",\"authors\":\"E. Chourdakis, J. Reiss\",\"doi\":\"10.18653/v1/W17-3905\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes a method for learning how to generate narrative by recombining sentences from a previous collection. Given a corpus of story events categorised into 9 topics, we approximate a deep reinforcement learning agent policy to recombine them in order to satisfy narrative structure. We also propose an evaluation of such a system. The evaluation is based on coherence, interest, and topic, in order to figure how much sense the generated stories make, how interesting they are, and examine whether new narrative topics can emerge.\",\"PeriodicalId\":162824,\"journal\":{\"name\":\"CC-NLG@INLG\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"CC-NLG@INLG\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/W17-3905\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"CC-NLG@INLG","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/W17-3905","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Constructing narrative using a generative model and continuous action policies
This paper proposes a method for learning how to generate narrative by recombining sentences from a previous collection. Given a corpus of story events categorised into 9 topics, we approximate a deep reinforcement learning agent policy to recombine them in order to satisfy narrative structure. We also propose an evaluation of such a system. The evaluation is based on coherence, interest, and topic, in order to figure how much sense the generated stories make, how interesting they are, and examine whether new narrative topics can emerge.