In social settings, much of human behavior is governed by unspoken rules of conduct rooted in societal norms. For artificial systems to be fully integrated into social environments, adherence to such norms is a central prerequisite. To investigate wh
ether language generation models can serve as behavioral priors for systems deployed in social settings, we evaluate their ability to generate action descriptions that achieve predefined goals under normative constraints. Moreover, we examine if models can anticipate likely consequences of actions that either observe or violate known norms, or explain why certain actions are preferable by generating relevant norm hypotheses. For this purpose, we introduce Moral Stories, a crowd-sourced dataset of structured, branching narratives for the study of grounded, goal-oriented social reasoning. Finally, we propose decoding strategies that combine multiple expert models to significantly improve the quality of generated actions, consequences, and norms compared to strong baselines.
This paper explores character-driven story continuation, in which the story emerges through characters' first- and second-person narration as well as dialogue---requiring models to select language that is consistent with a character's persona and the
ir relationships with other characters while following and advancing the story. We hypothesize that a multi-task model that trains on character dialogue plus character relationship information improves transformer-based story continuation. To this end, we extend the Critical Role Dungeons and Dragons Dataset (Rameshkumar and Bailey, 2020)---consisting of dialogue transcripts of people collaboratively telling a story while playing the role-playing game Dungeons and Dragons---with automatically extracted relationships between each pair of interacting characters as well as their personas. A series of ablations lend evidence to our hypothesis, showing that our multi-task model using character relationships improves story continuation accuracy over strong baselines.
Story visualization is an underexplored task that falls at the intersection of many important research directions in both computer vision and natural language processing. In this task, given a series of natural language captions which compose a story
, an agent must generate a sequence of images that correspond to the captions. Prior work has introduced recurrent generative models which outperform text-to-image synthesis models on this task. However, there is room for improvement of generated images in terms of visual quality, coherence and relevance. We present a number of improvements to prior modeling approaches, including (1) the addition of a dual learning framework that utilizes video captioning to reinforce the semantic alignment between the story and generated images, (2) a copy-transform mechanism for sequentially-consistent story visualization, and (3) MART-based transformers to model complex interactions between frames. We present ablation studies to demonstrate the effect of each of these techniques on the generative power of the model for both individual images as well as the entire narrative. Furthermore, due to the complexity and generative nature of the task, standard evaluation metrics do not accurately reflect performance. Therefore, we also provide an exploration of evaluation metrics for the model, focused on aspects of the generated frames such as the presence/quality of generated characters, the relevance to captions, and the diversity of the generated images. We also present correlation experiments of our proposed automated metrics with human evaluations.
Using topic modeling and lexicon-based word similarity, we find that stories generated by GPT-3 exhibit many known gender stereotypes. Generated stories depict different topics and descriptions depending on GPT-3's perceived gender of the character i
n a prompt, with feminine characters more likely to be associated with family and appearance, and described as less powerful than masculine characters, even when associated with high power verbs in a prompt. Our study raises questions on how one can avoid unintended social biases when using large language models for storytelling.
The study aimed to: develop a list of educational values to be met
in the stories for the children of Riyadh and in the light of national
standards, also aimed to find out the role of the stories in the
promotion of values.
High rise buildings have an obvious effect on modern architecture. They raised an
argumentation among various segments of society, specialists in forefront of them are
architects and planners, in addition to an ordinary people. Administrative bodie
s and the
public opinion involved many times in such matter especially in traditional character cities
which have an architectural rootage.
According to modern era features, high-rise buildings become a reality that couldn't
be ignored worldwide, including developing countries. At the same time, it is not a destiny
that couldn't be avoided, where many factors, cultural, social, economic, or technical,
collectively or separately, plays a big role in adopting or avoiding such choice.
Our research exposes this significant architecture subject, according to the principles
and data of modern age, whereas it reviews the most important concepts and principles
connected to it. Moreover, some of the most important experiments in this field are
addressed through it the pros and cons that surrounded this topic especially in developing
countries.
This study tries to show the importance of the story title and its
significance in children's stories. It displays the sense of the subject and
point to the resources of titles of the children's stories, through critical
studying of groups of children's stories in the Arab world.
