AutoText: An End-to-End AutoAI Framework for Text

被引：0

作者：

Chaudhary, Arunima ^{[1
]}

Issak, Alayt ^{[1
,2
,3
]}

Kate, Kiran ^{[1
]}

Katsis, Yannis ^{[1
]}

Valente, Abel ^{[1
]}

Wang, Dakuo ^{[1
]}

Evfimievski, Alexandre ^{[1
]}

Gurajada, Sairam ^{[1
]}

Kawas, Ban ^{[1
]}

Malossi, Cristiano ^{[1
]}

Popa, Lucian ^{[1
]}

Pedapati, Tejaswini ^{[1
]}

Samulowitz, Horst ^{[1
]}

Wistuba, Martin ^{[1
]}

Li, Yunyao ^{[1
]}

机构：

[1] IBM Res AI, Armonk, NY 10504 USA

[2] IBM Res, Armonk, NY USA

[3] Coll Wooster, Wooster, OH 44691 USA

来源：

THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | 2021年 / 35卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Building models for natural language processing (NLP) tasks remains a daunting task for many, requiring significant technical expertise, efforts, and resources. In this demonstration, we present AutoText, an end-to-end AutoAI framework for text, to lower the barrier of entry in building NLP models. AutoText combines state-of-the-art AutoAI optimization techniques and learning algorithms for NLP tasks into a single extensible framework. Through its simple, yet powerful UI, non-AI experts (e.g., domain experts) can quickly generate performant NLP models with support to both control (e.g., via specifying constraints) and understand learned models.

引用

页码：16001 / 16003

页数：3

共 50 条

[1] AutoAI: Automating the End-to-End AI Lifecycle with Humans-in-the-Loop
Wang, Dakuo
Ram, Parikshit
Weidele, Daniel Karl, I
Liu, Sijia
Muller, Michael
Weisz, Justin D.
Valente, Abel
Chaudhary, Arunima
Torres, Dustin
Samulowitz, Horst
Amini, Lisa
PROCEEDINGS OF THE 25TH INTERNATIONAL CONFERENCE ON INTELLIGENT USER INTERFACES COMPANION (IUI'20), 2020, : 77 - 78
[2] TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting
Feng, Wei
He, Wenhao
Yin, Fei
Zhang, Xu-Yao
Liu, Cheng-Lin
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9075 - 9084
[3] Text2Video: An End-to-end Learning Framework for Expressing Text With Videos
Yang, Xiaoshan
Zhang, Tianzhu
Xu, Changsheng
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 20 (09) : 2360 - 2370
[4] A Multi-Level Optimization Framework for End-to-End Text Augmentation
Somayajula, Sai Ashish
Song, Linfeng
Xie, Pengtao
TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2022, 10 : 343 - 358
[5] END-TO-END CHINESE TEXT RECOGNITION
Hu, Jie
Guo, Tszhang
Cao, Ji
Zhang, Changshui
2017 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2017), 2017, : 1407 - 1411
[6] An End-to-End Attack on Text CAPTCHAs
Zi, Yang
Gao, Haichang
Cheng, Zhouhang
Liu, Yi
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2020, 15 : 753 - 766
[7] End-to-End Scene Text Recognition
Wang, Kai
Babenko, Boris
Belongie, Serge
2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2011, : 1457 - 1464
[8] An end-to-end text spotter with text relation networks
Jianguo Jiang
Baole Wei
Min Yu
Gang Li
Boquan Li
Chao Liu
Min Li
Weiqing Huang
Cybersecurity, 4
[9] An end-to-end text spotter with text relation networks
Jiang, Jianguo
Wei, Baole
Yu, Min
Li, Gang
Li, Boquan
Liu, Chao
Li, Min
Huang, Weiqing
CYBERSECURITY, 2021, 4 (01)
[10] An End-to-End Scene Text Recognition for Bilingual Text
Albalawi, Bayan M.
Jamal, Amani T.
Al Khuzayem, Lama A.
Alsaedi, Olaa A.
BIG DATA AND COGNITIVE COMPUTING, 2024, 8 (09)

← 1 2 3 4 5 →