Scones

Huang, Forrest; Schoop, Eldon; Ha, David; Canny, John

doi:10.1145/3377325.3377485

Cited by 23 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study is positioned at the intersection of natural language dialogue [21,40,45] and interactive machine learning [1,3,18,22,26], in which the outputs of a machine learning model are visually displayed to the user [14] or are used to select informative questions for the user [13]. Our study is close to the latter and shows a promising way to obtain knowledge from the user during dialogues.…”

Section: Knowledge Acquisition Through Dialogues Using Kgc Scoresmentioning

confidence: 79%

See 1 more Smart Citation

Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues

Komatani

Fujioka

Nakashima

et al. 2021

26th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

Building a perfect knowledge base in a certain domain is practically impossible, so it is effective for dialogue systems to acquire knowledge for enhancing an imperfect knowledge base through natural language dialogues with users. This paper proposes a framework for selecting questions for such knowledge acquisition when a knowledge graph is used as the knowledge base. The framework uses knowledge graph completion (KGC) for predicting new links that are likely to be correct and selects questions on the basis of the KGC scores. One of the problems with this framework is that questions with incorrect content might be selected, which often occurs when the link prediction performance is low, and this would reduce the users' willingness to engage in dialogues. To alleviate this problem, this paper presents two modifications to the KGC training: 1) creating pseudo entities having substrings of the names of the entities in the graph so that the entities whose names share substrings are connected and 2) limiting the range of negative sampling. Cross validation-based experiments we conducted showed that these modifications improved KGC performance. We also conducted a user study with crowdsourcing to investigate the subjective perception of the correctness of the predicted links. The results suggest that the model trained with the modifications is capable of avoiding questions with incorrect content. CCS CONCEPTS• Computing methodologies → Discourse, dialogue and pragmatics.

show abstract

Section: Knowledge Acquisition Through Dialogues Using Kgc Scoresmentioning

confidence: 79%

“…The spread of mobile phones and smart speakers has increased the use of UIs that have natural language dialogue functions [21,40,45]. Some people prefer a dialogue interface capable of natural language to graphical user interface such as a Web form, because it can be easily used in a mobile environment.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues

Komatani

Fujioka

Nakashima

et al. 2021

26th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

show abstract

“…Dove et al [209] surveyed to understand how design innovation is practiced in the ML domain in terms of user experience. [63], [70], [165], [174], [211] [124], [125], [128], [175], [217] [69], [112], [113], [118], [130], [131], [133], [135], [137], [140], [144], [152], [153], [155] [49], [57], [67], [98], [110], [114], [180], [192], [193], [203], [214], [215] [48], [59], [62], [75], [79], [111], [120], [156], [159], [185], [195], [197], [207], [218] [65], [83],…”

Section: Survey Resultsmentioning

confidence: 99%

“…Creative Sketching Partner [143] is a proof-of-concept intelligent interface to inspire designers while sketching. Scones [144] is a tool that generates and modifies sketches iteratively according to text descriptions. CQAVis [145] is an application to filter high-quality comments from online community question answering forums.…”

Section: Applicationsmentioning

confidence: 99%

“…Given that the majority in those sectors are not AI experts developing AI systems for them requires us to investigate the human aspect of such systems. Our analysis shows that application domains have specifically targeted gaming [63,70,165,174,211], interactive technologies [69,112,113,118,130,131,[133][134][135]137,140,144,152,153,155,212,213], medicine [49,57,67,110,114,180,192,193,203,214,215], psychiatry [98], music [65,83,85,102,153], sports [126], dating [60], video production [84], assistive technologies [2,80,86,88,89,…”

Section: Application Domainsmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Kaluarachchi

Reis

Nanayakkara

2021

Sensors

View full text Add to dashboard Cite

After Deep Learning (DL) regained popularity recently, the Artificial Intelligence (AI) or Machine Learning (ML) field is undergoing rapid growth concerning research and real-world application development. Deep Learning has generated complexities in algorithms, and researchers and users have raised concerns regarding the usability and adoptability of Deep Learning systems. These concerns, coupled with the increasing human-AI interactions, have created the emerging field that is Human-Centered Machine Learning (HCML). We present this review paper as an overview and analysis of existing work in HCML related to DL. Firstly, we collaborated with field domain experts to develop a working definition for HCML. Secondly, through a systematic literature review, we analyze and classify 162 publications that fall within HCML. Our classification is based on aspects including contribution type, application area, and focused human categories. Finally, we analyze the topology of the HCML landscape by identifying research gaps, highlighting conflicting interpretations, addressing current challenges, and presenting future HCML research opportunities.

show abstract

Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts

Tian¹,

Ha²

2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Computational creativity has contributed heavily to abstract art in modern era, allowing artists to create high quality, abstract two dimension (2D) arts with a high level of controllability and expressibility. However, even with computational approaches that have promising result in making concrete 3D art, computationally addressing abstract 3D art with highquality and controllability remains an open question. To fill this gap, we propose to explore computational creativity in making abstract 3D art by bridging evolution strategies (ES) and 3D rendering through customizable parameterization of scenes. We demonstrate that our approach is capable of placing semi-transparent triangles in 3D scenes that, when viewed from specified angles, render into films that look like artists' specification expressed in natural language. This provides a new way for the artist to easily express creativity ideas for abstract 3D art. The supplementary material, which contains code, animation for all figures, and more examples, is here: https://es3dart.github.io/. Figure 1: Our proposed method places semi-transparent triangles in three dimension (3D) spaces using Evolution Strategies (Tang, Tian, and Ha 2022; Hansen 2000; Hansen 2006). Leveraging ray-tracing based rendering Mitsuba 3 (Nimier-David et al. 2019; Jakob et al. 2022), the rendered film at possibly multiple cameras is compared with its corresponding, user-specified text prompt using distance between their representation embedded by CLIP (Radford et al. 2021). Such distances, aggregate by average, are used as the fitness in the sense of Evolution Strategies, which optimize the parameters of triangles to achieve better finesses.

show abstract

Scones

Cited by 23 publications

References 31 publications

Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues

Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts

Contact Info

Product

Resources

About