Stephen McGregor, Matthew Purver, Geraint A. Wiggins
This paper presents and evaluates a novel sys-tem for computer generated poetry. Framed within contemporary theoretical trends in the evaluation of computational creativity, we investigate how evidence of generative process influences readers’ opinions of computer generated textual output. In addition to a technical description of our system, we present re-sults from a study asking respondents to evaluate short computer generated poems prefaced with different types of descriptions, in some cases objectively presenting the poem as the product of a statistical analysis of corpora and in some cases subjectively presenting the computer as a self-aware agent.
{"title":"Process Based Evaluation of Computer Generated Poetry","authors":"Stephen McGregor, Matthew Purver, Geraint A. Wiggins","doi":"10.18653/v1/W16-5508","DOIUrl":"https://doi.org/10.18653/v1/W16-5508","url":null,"abstract":"This paper presents and evaluates a novel sys-tem for computer generated poetry. Framed within contemporary theoretical trends in the evaluation of computational creativity, we investigate how evidence of generative process influences readers’ opinions of computer generated textual output. In addition to a technical description of our system, we present re-sults from a study asking respondents to evaluate short computer generated poems prefaced with different types of descriptions, in some cases objectively presenting the poem as the product of a statistical analysis of corpora and in some cases subjectively presenting the computer as a self-aware agent.","PeriodicalId":415027,"journal":{"name":"Workshop on Computational Creativity in Natural Language Generation","volume":"22 6S 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115942632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Kumagai, I. Kobayashi, D. Mochihashi, H. Asoh, Tomoaki Nakamura, T. Nagai
We propose a method of probabilistic natural language generation observing both a syntactic structure and an input of situational content. We employed Monte Carlo Tree Search for this nontrivial search problem, employing context-free grammar rules as search operators and evaluating numerous putative generations from these two aspects using logistic regression and n -gram language model. Through several experiments, we confirmed that our method can effectively generate sentences with various words and phrasings.
{"title":"Human-like Natural Language Generation Using Monte Carlo Tree Search","authors":"K. Kumagai, I. Kobayashi, D. Mochihashi, H. Asoh, Tomoaki Nakamura, T. Nagai","doi":"10.18653/v1/W16-5502","DOIUrl":"https://doi.org/10.18653/v1/W16-5502","url":null,"abstract":"We propose a method of probabilistic natural language generation observing both a syntactic structure and an input of situational content. We employed Monte Carlo Tree Search for this nontrivial search problem, employing context-free grammar rules as search operators and evaluating numerous putative generations from these two aspects using logistic regression and n -gram language model. Through several experiments, we confirmed that our method can effectively generate sentences with various words and phrasings.","PeriodicalId":415027,"journal":{"name":"Workshop on Computational Creativity in Natural Language Generation","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128963614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Louisa Pragst, Juliana Miehle, Stefan Ultes, W. Minker
Comunicacio presentada a: INLG 2016 Workshop on Computational Creativity and Natural Language Generation, celebrat a Edinburgh, Escocia, del 5 al 8 de setembre de 2016.
{"title":"Automatic Modification of Communication Style in Dialogue Management","authors":"Louisa Pragst, Juliana Miehle, Stefan Ultes, W. Minker","doi":"10.18653/v1/W16-5506","DOIUrl":"https://doi.org/10.18653/v1/W16-5506","url":null,"abstract":"Comunicacio presentada a: INLG 2016 Workshop on Computational Creativity and Natural Language Generation, celebrat a Edinburgh, Escocia, del 5 al 8 de setembre de 2016.","PeriodicalId":415027,"journal":{"name":"Workshop on Computational Creativity in Natural Language Generation","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127559138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Storytelling systems are computational systems designed to tell stories. Every story generation system defines its specific knowledge representation for supporting the storytelling process. Thus, there is a shared need amongst all the systems: the knowledge must be expressed unambiguously to avoid inconsistencies. However, when trying to make a comparative assessment between the storytelling systems, there is not a common way for expressing this knowledge. That is when a form of expression that covers the different aspects of the knowledge representations becomes necessary. A suitable solution is the use of a Controlled Natural Language (CNL) which is a good half-way point between natural and formal languages. A CNL can be used as a common medium of expression for this heterogeneous set of systems. This paper proposes the use of Controlled Natural Language for expressing every storytelling system knowledge as a collection of natural language sentences. In this respect, an initial grammar for a CNL is proposed, focusing on certain aspects of this knowledge.
{"title":"Mining Knowledge in Storytelling Systems for Narrative Generation","authors":"Eugenio Concepción, Gonzalo Méndez, Pablo Gervás","doi":"10.18653/v1/W16-5507","DOIUrl":"https://doi.org/10.18653/v1/W16-5507","url":null,"abstract":"Storytelling systems are computational systems designed to tell stories. Every story generation system defines its specific knowledge representation for supporting the storytelling process. Thus, there is a shared need amongst all the systems: the knowledge must be expressed unambiguously to avoid inconsistencies. However, when trying to make a comparative assessment between the storytelling systems, there is not a common way for expressing this knowledge. That is when a form of expression that covers the different aspects of the knowledge representations becomes necessary. A suitable solution is the use of a Controlled Natural Language (CNL) which is a good half-way point between natural and formal languages. A CNL can be used as a common medium of expression for this heterogeneous set of systems. This paper proposes the use of Controlled Natural Language for expressing every storytelling system knowledge as a collection of natural language sentences. In this respect, an initial grammar for a CNL is proposed, focusing on certain aspects of this knowledge.","PeriodicalId":415027,"journal":{"name":"Workshop on Computational Creativity in Natural Language Generation","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132761524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We produced two stories by using a computer program and submitted them to the third Hoshi Shinichi Award, a Japanese literary award open to non-humans as well as humans. This paper reports what system we implemented for the submission and how we made the stories by using the system.
{"title":"A Challenge to the Third Hoshi Shinichi Award","authors":"Satoshi Sato","doi":"10.18653/v1/W16-5505","DOIUrl":"https://doi.org/10.18653/v1/W16-5505","url":null,"abstract":"We produced two stories by using a computer program and submitted them to the third Hoshi Shinichi Award, a Japanese literary award open to non-humans as well as humans. This paper reports what system we implemented for the submission and how we made the stories by using the system.","PeriodicalId":415027,"journal":{"name":"Workshop on Computational Creativity in Natural Language Generation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129349368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The paper presents a reconstruction of the automatic poetry generation system realized in Italy in 1961 by Nanni Balestrini to compose the poem Tape Mark I. The major goal of the paper is to provide a critical comparison between the high-level approach that seems to be suggested by the poet, and the low-level combinatorial algorithm that was actually implemented. This comparison allows to assess the relevance of how the available technology constrained and shaped the work of the poet, to reveal some of his aesthetic assumptions, and to discuss some aspects of the relation between human and the machine in the creative process.
本文介绍了1961年由南尼·巴莱斯里尼(Nanni Balestrini)在意大利实现的诗歌自动生成系统的重建，以创作诗歌《磁带标记1》(Tape Mark i)。本文的主要目标是提供诗人建议的高级方法与实际实现的低级组合算法之间的关键比较。这种比较可以评估现有技术如何限制和塑造诗人作品的相关性，揭示他的一些美学假设，并讨论在创作过程中人与机器之间关系的某些方面。
{"title":"Combinatorics vs Grammar: Archeology of Computational Poetry in Tape Mark I","authors":"A. Mazzei, Andrea Valle","doi":"10.18653/v1/W16-5509","DOIUrl":"https://doi.org/10.18653/v1/W16-5509","url":null,"abstract":"The paper presents a reconstruction of the automatic poetry generation system realized in Italy in 1961 by Nanni Balestrini to compose the poem Tape Mark I. The major goal of the paper is to provide a critical comparison between the high-level approach that seems to be suggested by the poet, and the low-level combinatorial algorithm that was actually implemented. This comparison allows to assess the relevance of how the available technology constrained and shaped the work of the poet, to reveal some of his aesthetic assumptions, and to discuss some aspects of the relation between human and the machine in the creative process.","PeriodicalId":415027,"journal":{"name":"Workshop on Computational Creativity in Natural Language Generation","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115659025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A model is proposed showing how automatically extracted and manually written association rules can be used to build the structure of a narrative from real-life temporal data. The generated text’s communicative goal is to help the reader construct a causal representation of the events. A connecting associative thread allows the reader to follow associations from the beginning to the end of the text. It is created using a spanning tree over a selected associative sub-network. The results of a text quality evaluation show that the texts were understandable, but that flow between sentences, although not bad, could still be improved.
{"title":"Assembling Narratives with Associative Threads","authors":"Pierre-Luc Vaudry, G. Lapalme","doi":"10.18653/v1/W16-5501","DOIUrl":"https://doi.org/10.18653/v1/W16-5501","url":null,"abstract":"A model is proposed showing how automatically extracted and manually written association rules can be used to build the structure of a narrative from real-life temporal data. The generated text’s communicative goal is to help the reader construct a causal representation of the events. A connecting associative thread allows the reader to follow associations from the beginning to the end of the text. It is created using a spanning tree over a selected associative sub-network. The results of a text quality evaluation show that the texts were understandable, but that flow between sentences, although not bad, could still be improved.","PeriodicalId":415027,"journal":{"name":"Workshop on Computational Creativity in Natural Language Generation","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129194763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Our software system simulates the classical collaborative Japanese poetry form, renga, made of linked haikus. We used NLP methods wrapped up as web services. Our experiments were only a partial success, since results fail to satisfy classical constraints. To gather ideas for future work, we examine related research in semiotics, linguistics, and computing.
{"title":"X575: Writing rengas with web services","authors":"J. Corneli, D. Winterstein","doi":"10.18653/v1/W16-5504","DOIUrl":"https://doi.org/10.18653/v1/W16-5504","url":null,"abstract":"Our software system simulates the classical collaborative Japanese poetry form, renga, made of linked haikus. We used NLP methods wrapped up as web services. Our experiments were only a partial success, since results fail to satisfy classical constraints. To gather ideas for future work, we examine related research in semiotics, linguistics, and computing.","PeriodicalId":415027,"journal":{"name":"Workshop on Computational Creativity in Natural Language Generation","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123971356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Stories are sequential in nature but they are used to package human experience that involves many things happening at the same time, to several people or in several locations. The mechanics of this packaging process constitute an instance of content planning that has not ben addressed in sufficient detail in existing NLG work. The present paper reviews a number of traditional stories in the light of the basic concepts of narratology that would be involved in the decisions involved in planning the content for tellings of these stories, proposes a number of basic principles to understand what is happening, and explores a possible way in which these principles may translate to basic heuristics for narrative content planning.
{"title":"Empirical Determination of Basic Heuristics for Narrative Content Planning","authors":"Pablo Gervás","doi":"10.18653/v1/W16-5503","DOIUrl":"https://doi.org/10.18653/v1/W16-5503","url":null,"abstract":"Stories are sequential in nature but they are used to package human experience that involves many things happening at the same time, to several people or in several locations. The mechanics of this packaging process constitute an instance of content planning that has not ben addressed in sufficient detail in existing NLG work. The present paper reviews a number of traditional stories in the light of the basic concepts of narratology that would be involved in the decisions involved in planning the content for tellings of these stories, proposes a number of basic principles to understand what is happening, and explores a possible way in which these principles may translate to basic heuristics for narrative content planning.","PeriodicalId":415027,"journal":{"name":"Workshop on Computational Creativity in Natural Language Generation","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129787707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：