TY - GEN
T1 - AILA
T2 - 2019 CHI Conference on Human Factors in Computing Systems, CHI 2019
AU - Choi, Minsuk
AU - Park, Cheonbok
AU - Yang, Soyoung
AU - Kim, Yonggyu
AU - Choo, Jaegul
AU - Hong, Sungsoo
N1 - Funding Information:
This work was partially supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP) (No. NRF-2016R1C1B2015924) and R&D program for Advanced Integrated-intelligence for IDentification (AIID) through the NRF funded by Ministry of Science and ICT (2018M3E3A1057288).
Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/5/2
Y1 - 2019/5/2
N2 - Document labeling is a critical step in building various machine learning applications. However, the step can be time-consuming and arduous, requiring a significant amount of human effort. To support an efficient document labeling environment, we present a system called Attentive Interactive Labeling Assistant (AILA). At its core, AILA uses Interactive Attention Module (IAM), a novel module that visually highlights words in a document that labelers may pay attention to when labeling a document. IAM utilizes attention-based Deep Neural Networks, which not only support a prediction of which words to highlight, but also enable labelers to indicate words that should be assigned high attention weights while labeling to improve the future quality of word prediction. We evaluated the labeling efficiency and accuracy by comparing the conditions with and without IAM in our study. The results showed that the participants’ labeling efficiency increased significantly under the condition with IAM than under the condition without IAM, while the two conditions maintained roughly the same labeling accuracy.
AB - Document labeling is a critical step in building various machine learning applications. However, the step can be time-consuming and arduous, requiring a significant amount of human effort. To support an efficient document labeling environment, we present a system called Attentive Interactive Labeling Assistant (AILA). At its core, AILA uses Interactive Attention Module (IAM), a novel module that visually highlights words in a document that labelers may pay attention to when labeling a document. IAM utilizes attention-based Deep Neural Networks, which not only support a prediction of which words to highlight, but also enable labelers to indicate words that should be assigned high attention weights while labeling to improve the future quality of word prediction. We evaluated the labeling efficiency and accuracy by comparing the conditions with and without IAM in our study. The results showed that the participants’ labeling efficiency increased significantly under the condition with IAM than under the condition without IAM, while the two conditions maintained roughly the same labeling accuracy.
KW - Attention model
KW - Deep neural networks
KW - Document classification
KW - Document labeling
KW - Natural language processing
UR - http://www.scopus.com/inward/record.url?scp=85067603145&partnerID=8YFLogxK
U2 - 10.1145/3290605.3300460
DO - 10.1145/3290605.3300460
M3 - Conference contribution
AN - SCOPUS:85067603145
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI 2019 - Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
Y2 - 4 May 2019 through 9 May 2019
ER -