Digital Library[ Search Result ]
Denoising Method for Document Grounded Conversation Datasets via Back Translation Process
Damrin Kim, Boeun Kim, Youngjin Jang, Harksoo Kim
http://doi.org/10.5626/JOK.2024.51.1.34
Document Grounded Conversation is a conversation between two or more speakers based on a given document. Document-based dialogue systems are tasks that generate responses to the last utterance of dialogue, and various document-based dialogue datasets in English have been released and actively studied. Notably, There is no active research in Korean that has been conducted due to the absence of a document-based conversation dataset in Korean. While KoDoc2dial, which translates the English document-based conversation dataset Doc2dial into Korean, was recently released, it contains the noise generated during the translation process. The noise in the KoDoc2Dial should be reduced because noise-containing datasets can negatively affect training and system consistency aspects. In this paper, we propose a method for reducing the noise contained in the KoDoc2Dial through filtering using the reverse translation process. The results of the experiments showed that the method proposed in this paper had a performance improvement of about 3.6%p in SacreBLEU compared to before filtering.
A Span Matrix-based Answer Candidates Detection Model used 2-Step Learning
Boeun Kim, Youngjin Jang, Harksoo Kim
http://doi.org/10.5626/JOK.2021.48.5.539
Automatic data construction refers to a technology that automatically constructs data through algorithms or deep neural networks. The automated construction system of question-answer data aimed at in this paper was mainly studied through a question generation model, which signifies a model that generates questions related to a given paragraph. Previously, paragraph and answer candidates were entered into the question generation model and related questions were generated. The answer candidates" input to the question generation model was detected through a rule-based method or a method using a deep neural network. We judged that answer detection, which is a subtask of question generation, will have a great influence on question generation. Consequently, we have proposed answer candidates detection model and 2-step learning method using Span Matrix. An experiment was conducted to find out how the questions generated through various methods of extracting answer candidates affect the question-answering system. The proposed model extracted a large number of correct answers compared to the existing model, and the noise in the learning process was supplemented by using the entity name dataset. Apparently, it was confirmed that the question-answer data generated as answer candidates extracted by the proposed model contributed the most to the performance of the question-answer system.
Modeling of Visual Attention Probability for Stereoscopic Videos and 3D Effect Estimation Based on Visual Attention
Boeun Kim, Wonseok Song, Taejeong Kim
Viewers of videos are likely to absorb more information from the part of the screen that attracts visual attention. This fact has led to the visual attention models that are being used in producing and evaluating videos. In this paper, we investigate the factors that are significant to visual attention and the mathematical form of the visual attention model. We then estimated the visual attention probability using the statistical design of experiments. The analysis of variance (ANOVA) verifies that the motion velocity, distance from the screen, and amount of defocus blur affect human visual attention significantly. Using the response surface modeling (RSM), we created a visual attention score model that concerns the three factors, from which we calculate the visual attention probabilities (VAPs) of image pixels. The VAPs are directly applied to existing gradient based 3D effect perception measurement. By giving weights according to our VAPs, our algorithm achieves more accurate measurement than the existing method. The performance of the proposed measurement is assessed by comparing them with subjective evaluation as well as with existing methods. The comparison verifies that the proposed measurement outperforms the existing ones.
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