Digital Library[ Search Result ]
R²FID: Joint Reranker in Fusion-In-Decoder for Open Domain Question Answering over Tables
Sung-Min Lee, Eunhwan Park, Daeryong Seo, Donghyeon Jeon, Inho Kang, Seung-Hoon Na
http://doi.org/10.5626/JOK.2023.50.10.874
Open Domain Question Answering is a challenging problem that aims to generate an answer where reference documents relevant to a question are not provided. Considering that the importance of the QA system in structured data such as tables has recently gradually increased, this paper presents a method for table open domain question answering of Korean, focusing on tabular contents appearing in Wikipedia. In addition, we extensively apply the Joint Reranker based Fusion-In-Decoder to address limitations entailed in table retrieval, Resulting methods based on Joint Reranker led to improvements of an EM of 3.36 and a F1-Score of 3.25 over open domain question answering tasks.
Interactive Visual Analytics System for Criminal Intelligence Analysts with Multiple Coordinated Views
Seokweon Jung, Donghwa Shin, Jinwook Bok, Seokhyeon Park, Hyeon Jeon, Jinwook Seo, Insoo Lee, Sooyoung Park
http://doi.org/10.5626/JOK.2023.50.1.47
Data that criminal intelligence analysts have to analyze have become much larger and more complex in recent decades. However, the environment and methods of investigation have not yet kept up with those changes. In this study, we examined current investigation practices in Korean Government Agency. We focused on the sensemaking process of investigation and tried to adopt visual analytics approaches for sensemaking into the investigation. We derived tasks and design requirements and designed a multi-view visual analytics system that could satisfy them. We validated our design with a high-fidelity prototype through a case study to show realistic use cases.
Dynamic Decision Making for Self-Adaptive Systems Considering Environment Information
Misoo Kim, Hohyeon Jeong, Eunseok Lee
Self-adaptive systems (SASs) can change their goals and behaviors to achieve its ultimate goal in a dynamic execution environment. Existing approaches have designed, at the design time, utility functions to evaluate and predict the goal satisfaction, and set policies that are crucial to achieve each goal. The systems can be adapted to various runtime environments by utilizing the pre-defined utility functions and policies. These approaches, however, may or may not guarantee the proper adaptability, because system designers cannot assume and predict all system environment perfectly at the design time. To cope with this problem, this paper proposes a new method of dynamic decision making, which takes the following steps: firstly we design a Dynamic Decision Network (DDN) with environmental data and goal model that reflect system contexts; secondly, the goal satisfaction is evaluated and predicted with the designed DDN and real-time environmental information. We furthermore propose a dynamic reflection method that changes the model by using newly generated data in real-time. The proposed method was actually applied to ROBOCODE, and verified its effectiveness by comparing to conventional static decision making.
An Extended DDN based Self-Adaptive System
Misoo Kim, Hohyeon Jeong, Eunseok Lee
In order to solve problems happening in the practical environment of complicated system, the importance of the self-adaptive system has recently begun to emerge. However, since the differences between the model built at the time of system design and the practical environment can lead the system into unpredictable situations, the study into methods of dealing with it is also emerging as an important issue. In this paper, we propose a method for deciding on the adaptation time in an uncertain environment, and reflecting the real-time environment in the system’s model. The proposed method calculates the Bayesian Surprise for the suitable adaptation time by comparing previous and current states, and then reflects the result following the performed policy in the design model to help in deciding the proper policy for the actual environment. The suggested method is applied to a navigation system to confirm its effectiveness.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr