Fig 3 - uploaded by Kevin Bowden
Content may be subject to copyright.
Source publication
Storytelling serves many different social functions, e.g. stories are used to persuade, share troubles, establish shared values, learn social behaviors, and entertain. Moreover, stories are often told conversationally through dialog, and previous work suggests that information provided dialogically is more engaging than when provided in monolog. In...
Context in source publication
Context 1
... are generated by performing a series of pruning operations based on the class of the selected node and the relationship with its parent and siblings. For example, if store in Figure 3 is selected, we identify this node as our ques- tion. The class of a node indicates the rules our system must follow when making deletions. ...
Citations
... The storytelling map technique is an advanced method for conveying messages to users directly on a geospatial basis [33]. Storytelling maps contain stories in which there are maps (geospatial information) or geospatial data and story narratives made for the purpose of conveying problems, spreading knowledge, and so on [34]. By producing maps that can be read and understood by the public, it is hoped that the spread of this virus can be suppressed and in areas where there are not many cases, additional cases of its spread can be minimized. ...
The COVID-19 pandemic continues to increase, transmission, spread, and death rates are increasing, resulting in the implementation of large-scale social restrictions on community activities in Indonesia. This high rate of transmission can be caused by poor public behavior towards prevention programs that have been announced by the Government. In order to increase public knowledge in prevention and communication and minimize the spread of COVID-19, socialization and outreach media are needed that can encourage more effective delivery and dissemination of information. Technological developments encourage the delivery of information to become more interactive. One use of technology is delivering information with spatial integration through ArcGIS Story Maps. Story Maps can be handy for spreading knowledge on several topics, focusing on where the story occurs. In this paper, we explore the opportunities offered by Story Maps to implement Story Maps as an outreach media and a solution for socializing and disseminating information during the pandemic. Specifically, we refer to a series of different applications offered by Esri for building Story Maps based on different approaches and techniques. The results of using Story Maps are in the form of presenting information, information media, and counseling in the form of an interactive map which contains a general description of COVID-19, case conditions, level of spread, and how to handle it and related regulations through the Story Maps feature. This story map involves geospatial elements, web GIS, text, images, and video so that it can be an alternative solution for related parties in socializing and disseminating information during the pandemic
... Teknik storytelling map merupakan metode tingkat lanjut untuk menyampaikan pesan pada pengguna secara langsung berbasis geospasial [6]. Storytelling map berisi tentang cerita yang di dalamnya terdapat peta (informasi geospasial) atau data geospasial dan narasi cerita dibuat bertujuan untuk menyampaikan masalah, menyebarkan pengetahuan, dan sebagainya [7]. Dengan dihasilkanya peta yang dapat dibaca dan dipahami oleh masyarakat, diharapakna penyebaran virus ini dapat ditekan dan wilayah yang belum banyak kasusnya, dapat diminimalisir penambahan kasus penyebarannya. ...
Pandemi Corona Virus (COVID-19) terus meningkat, angka penularan, penyebaran, dan kematian yang semakin tinggi sehingga pemerintah menerapkan pembatasan sosial berskala besar pada aktivitas masyarakat di Indonesia. Penularan yang tinggi ini bisa disebabkan oleh perilaku masyarakat yang kurang baik terhadap program pencegahan yang sudah di informasikan oleh Pemerintah, oleh sebab itu perlu dilakukannya penyebaran dan penyuluhan terkait COVID-19 untuk meningkatkan pengetahuan masyarakat dalam pencegahan dan penularan agar bisa meminimalisir penyebaran COVID-19. Perkembangan teknologi telah mendorong penyampaian informasi menjadi lebih interaktif. Salah satu pemanfaatan teknologi adalah penyampaian informasi spasial melalui ArcGIS Story Maps. ArcGIS Story maps merupakan cara untuk memvisualisasikan peta dan data nonspasial pada aplikasi web tingkat lanjut. Kegiatan ini dilakukan dengan sosialisasi secara tidak langsung dengan penyajian sarana media informasi dan penyuluhan menggunakan Story maps. Hasil pengabdian ini menunjukkan bahwa media yang berisi peta interaktif tentang gambaran umum COVID-19, kondisi kasus, tingkat sebaran kasus dan cara penanganan hingga aturan terkait dengan memanfaatkan fitur Story maps dapat digunakan sebagai sarana dalam penyajian informasi dan penyuluhan di masa pandemi dan dapat membantu instansi terkait dalam melakukan sosialisasi secara tidak langsung dan percepatan penyebaran informasi ke masyarakat
... Then, it simulates the correlation between characters' interactions and their affinity levels. Dialogue: Rendering a story as dialogue produces more engagement to the listener [27]. Bowden et al. [27] presented algorithms for converting a deep representation of a story into dialogic storytelling. ...
... Dialogue: Rendering a story as dialogue produces more engagement to the listener [27]. Bowden et al. [27] presented algorithms for converting a deep representation of a story into dialogic storytelling. Their system is capable of telling a story in different settings to different audiences. ...
Computational generation of stories is a subfield of computational creativity where artificial intelligence and psychology intersect to teach computers how to mimic humans’ creativity. It helps generate many stories with minimum effort and customize the stories for the users’ education and entertainment needs. Although the automatic generation of stories started to receive attention many decades ago, advances in this field to date are less than expected and suffer from many limitations. This survey presents an extensive study of research in the area of non-interactive textual story generation, as well as covering resources, corpora, and evaluation methods that have been used in those studies. It also shed light on factors of story interestingness.
... Many subsequent studies were developed as extensions of PERSONAGE. These include a wide range of improvements on the system architecture and support to additional personality traits [17], and its application to other domains such as gossip generation [22], computer game dialogues [23], creative writing [24], storytelling [25], gesture generation [26] and customer feedback generation [18], among others. Generally speaking, however, the relation between personality and content determination is not the focus of any of these studies. ...
Abstract This paper focuses on the computer side of human-computer interaction through natural language, which is the domain of natural language generation (NLG) studies. From a given (usually non-linguistic) input, NLG systems will in principle generate the same fixed text as an output and in order to attain more natural or human-like interaction will often resort to a wide range of strategies for stylistic variation. Among these, the use of computational models of human personality has emerged as a popular alternative in the field and will be the focus of the present work as well. More specifically, the present study describes two machine learning experiments to establish possible relations between personality and content selection (as opposed to the more well-documented relation between personality and surface realisation), and it is, to the best of our knowledge, the first of its kind to address this issue at both macro and micro planning levels, which may arguably pave the way for the future development of more robust personality-dependent systems of this kind.
... Stylistic Variation: When realizing our top response candidate, we use a statistical natural language generation engine [6] to add variation in a way which seems to increase the coherence of the response. Our most common use case is prepending our response with an acknowledgement hedge -enabling a more natural transition between topics. ...
One of the most interesting aspects of the Amazon Alexa Prize competition is that the framing of the competition requires the development of new computational models of dialogue and its structure. Traditional computational models of dialogue are of two types: (1) task-oriented dialogue, supported by AI planning models,or simplified planning models consisting of frames with slots to be filled; or (2)search-oriented dialogue where every user turn is treated as a search query that may elaborate and extend current search results. Alexa Prize dialogue systems such as SlugBot must support conversational capabilities that go beyond what these traditional models can do. Moreover, while traditional dialogue systems rely on theoretical computational models, there are no existing computational theories that circumscribe the expected system and user behaviors in the intended conversational genre of the Alexa Prize Bots. This paper describes how UCSC's SlugBot team has combined the development of a novel computational theoretical model, Discourse Relation Dialogue Model, with its implementation in a modular system in order to test and refine it. We highlight how our novel dialogue model has led us to create a novel ontological resource, UniSlug, and how the structure of UniSlug determine show we curate and structure content so that our dialogue manager implements and tests our novel computational dialogue model.
... Pichotta and Mooney [2016] parse a large collection of natural language documents, extract sequences of events, and learn statistical models of them. Some recent work explored story generation with additional information (Bowden et al. 2016;Peng et al. 2018;Guan, Wang, and Huang 2019). Visual storytelling (Huang et al. 2016;Liu et al. 2016b;Wang et al. 2018) aims to generate humanlevel narrative language from a sequence of images. ...
Automatic storytelling is challenging since it requires generating long, coherent natural language to describes a sensible sequence of events. Despite considerable efforts on automatic story generation in the past, prior work either is restricted in plot planning, or can only generate stories in a narrow domain. In this paper, we explore open-domain story generation that writes stories given a title (topic) as input. We propose a plan-and-write hierarchical generation framework that first plans a storyline, and then generates a story based on the storyline. We compare two planning strategies. The dynamic schema interweaves story planning and its surface realization in text, while the static schema plans out the entire storyline before generating stories. Experiments show that with explicit storyline planning, the generated stories are more diverse, coherent, and on topic than those generated without creating a full plan, according to both automatic and human evaluations.
... Therefore, in order to make the conversation sound less robotic and more natural, we must detect user utterances which are not argumentatively sound and respond accordingly. Lukin et al.(2017) talk about the role of personality in persuasion [9] and Bowden et al.(2016) have shown that adding a layer of stylistic variation to a dialogue is sufficient for representing personality between speakers [5]. We intend to investigate how we can enhance the user's experience by entraining Debbie's personality with respect to the user's personality. ...
Chatbots are a rapidly expanding application of dialogue systems with companies switching to bot services for customer support, and new applications for users interested in casual conversation. One style of casual conversation is argument; many people love nothing more than a good argument. Moreover, there are a number of existing corpora of argumentative dialogues, annotated for agreement and disagreement, stance, sarcasm and argument quality. This paper introduces Debbie, a novel arguing bot, that selects arguments from conversational corpora, and aims to use them appropriately in context. We present an initial working prototype of Debbie, with some preliminary evaluation and describe future work.
... Stylistic Variation: When realizing our top response candidate, we use a statistical natural language generation engine [6] to add variation in a way which seems to increase the coherence of the response. Our most common use case is prepending our response with an acknowledgement hedge -enabling a more natural transition between topics. ...
One of the most interesting aspects of the Amazon Alexa Prize competition is that the framing of the competition requires the development of new computational models of dialogue and its structure. Traditional computational models of dialogue are of two types: (1) task-oriented dialogue, supported by AI planning models, or simplified planning models consisting of frames with slots to be filled; or (2) search-oriented dialogue where every user turn is treated as a search query that may elaborate and extend current search results. Alexa Prize dialogue systems such as SlugBot must support conversational capabilities that go beyond what these traditional models can do. Moreover, while traditional dialogue systems rely on theoretical computational models, there are no existing computational theories that circumscribe the expected system and user behaviors in the intended conversational genre of the Alexa Prize Bots. This paper describes how UCSC's SlugBot team has combined the development of a novel computational theoretical model, Discourse Relation Dialogue Model, with its implementation in a modular system in order to test and refine it. We highlight how our novel dialogue model has led us to create a novel ontological resource, UniSlug, and how the structure of UniSlug determines how we curate and structure content so that our dialogue manager implements and tests our novel computational dialogue model.
... Other systems using plan-based strategies can develop a plan composed of a series of (dialogue) actions, to reach goals in hierarchical tasks [2]. Bowden et al. [3] present algorithms for generating dialogues by converting a deep representation made by annotating and processing a story semantically [8,23]. ...
... Pichotta and Mooney [2016] parse a large col- lection of natural language documents, extract sequences of events, and learn statistical models of them. Some re- cent work explored story generation with additional infor- mation ( Bowden et al. 2016;Peng et al. 2018;Guan, Wang, and Huang 2019). Visual storytelling ( Huang et al. 2016;Liu et al. 2016b;Wang et al. 2018) aims to generate human- level narrative language from a sequence of images. ...
Automatic storytelling is challenging since it requires generating long, coherent natural language to describes a sensible sequence of events. Despite considerable efforts on automatic story generation in the past, prior work either is restricted in plot planning, or can only generate stories in a narrow domain. In this paper, we explore open-domain story generation that writes stories given a title (topic) as input. We propose a plan-and-write hierarchical generation framework that first plans a storyline, and then generates a story based on the storyline. We compare two planning strategies. The dynamic schema interweaves story planning and its surface realization in text, while the static schema plans out the entire storyline before generating stories. Experiments show that with explicit storyline planning, the generated stories are more diverse, coherent, and on topic than those generated without creating a full plan, according to both automatic and human evaluations.
