INTENT: Interactive Tensor Transformation Synthesis

INTENT: Interactive Tensor Transformation Synthesis
复制标题

意图:交互式张量变换合成

DOI:
10.1145/3526113.3545653
复制
发表时间:
2022
期刊:
Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology
影响因子:
--
通讯作者:
Zhang, Tianyi
Zhang, Tianyi
中科院分区:
--
文献类型:
--
作者:
Zhou, Zhanhui;Tang, Man To;Pan, Qiping;Tan, Shangyin;Wang, Xinyu;Zhang, Tianyi

文献摘要

参考文献

被引文献

相似文献

由于深度学习(DL)在许多领域的上级性能,人们对采用它的兴趣越来越大。然而,现代DL框架(如TensorFlow)通常具有陡峭的学习曲线。在这项工作中,我们提出了INTENT,一个交互式系统,推断用户的意图,并代表用户生成相应的TensorFlow代码。INTENT通过使用中间结果和元素数据出处呈现各个张量变换步骤,帮助用户理解和验证生成代码的语义。用户可以通过将某些TensorFlow运算符标记为需要或不需要,或直接操作生成的代码来进一步指导INTENT。一项有18名参与者的受试者内用户研究表明,与没有交互或可视化支持的INTENT变体相比,用户只需一半的时间就可以更成功地完成TensorFlow中的编程任务。
There is a growing interest in adopting Deep Learning (DL) given its superior performance in many domains. However, modern DL frameworks such as TensorFlow often come with a steep learning curve. In this work, we propose INTENT, an interactive system that infers user intent and generates corresponding TensorFlow code on behalf of users. INTENT helps users understand and validate the semantics of generated code by rendering individual tensor transformation steps with intermediate results and element-wise data provenance. Users can further guide INTENT by marking certain TensorFlow operators as desired or undesired, or directly manipulating the generated code. A within-subjects user study with 18 participants shows that users can finish programming tasks in TensorFlow more successfully with only half the time, compared with a variant of INTENT that has no interaction or visualization support.
可解释的程序综合
DOI: 10.1145/3411764.3445646
发表时间: 2021
期刊: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems
影响因子: --
作者:
Tianyi Zhang;Zhiyang Chen;Yuanli Zhu;Priyan Vaithilingam;Xinyu Wang;Elena L. Glassman
通讯作者: Elena L. Glassman
DOI: 10.1109/issre.2019.00020
发表时间: 2019-10
期刊: 2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE)
影响因子: --
作者:
Tianyi Zhang;Cuiyun Gao;Lei Ma;Michael R. Lyu;Miryung Kim
通讯作者: Tianyi Zhang;Cuiyun Gao;Lei Ma;Michael R. Lyu;Miryung Kim
DOI: 10.1109/icse-seip52600.2021.00033
发表时间: 2021
期刊: 2021 IEEE/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)
影响因子: --
作者:
["Zejun Zhang
通讯作者: ["Zejun Zhang
APPINITE:使用自然语言指令通过演示指定编程中的数据描述的多模式接口
DOI: 10.1109/vlhcc.2018.8506506
发表时间: 2018
期刊: 2018 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC'18
影响因子: --
作者:
Li, Toby Jia-Jun;Labutov, Igor;Li, Xiaohan Nancy;Zhang, Xiaoyi;Shi, Wenze;Ding, Wanling;Mitchell, Tom M.;Myers, Brad A.
通讯作者: Myers, Brad A.
通过示例实现丰富多彩的文本处理方法
DOI: 10.1145/2501988.2502040
发表时间: 2013
期刊: Proceedings of the 26th annual ACM symposium on User interface software and technology
影响因子: --
作者:
Kuat Yessenov;Shubham Tulsiani;A. Menon;Rob Miller;Sumit Gulwani;B. Lampson;A. Kalai
通讯作者: A. Kalai