Digital Library[ Search Result ]
Enhancing LLM-based Zero-Shot Conversational Recommendation via Reasoning Path
Heejin Kook, Seongmin Park, Jongwuk Lee
http://doi.org/10.5626/JOK.2025.52.7.617
Conversational recommender systems provide personalized recommendations through bi-directional interactions with users. Traditional conversational recommender systems rely on external knowledge, such as knowledge graphs, to effectively capture user preferences. While recent rapid advancement of large language models has enabled zero-shot recommendations, challenges remain in understanding users' implicit preferences and designing optimal reasoning paths. To address these limitations, this study investigates the importance of appropriate reasoning path construction in zero-shot based conversational recommender systems and explores the potential of using a new approach based on this foundation. The proposed framework consists of two stages: (1) comprehensively extracting both explicit and implicit preferences from conversational context, and (2) constructing reasoning trees to select optimal reasoning paths based on these preferences. Experimental results on benchmark datasets INSPIRED and ReDial show that our proposed method achieves up to 11.77% improvement in Recall@10 compared to existing zero-shot methods, It even outperforms some learning-based models.
Time Series Data Imbalance Resolution Techniques for Early Prediction
Eungseon An, Taehyoung Kwon, Doguk Kim
http://doi.org/10.5626/JOK.2025.52.7.593
Time series forecasting is a critical task that involves analyzing observed time series data to predict future values. However, when dealing with imbalanced data, model performance can degrade, leading to biased predictions. Although recent studies have explored various deep learning techniques and data augmentation methods, many fail to address challenges posed by data imbalance and the intrinsic characteristics of time series data simultaneously, leaving underlying issues unresolved. This study proposed a novel approach that could leverage temporal patterns to generate synthetic samples and extend the scope of early prediction. By identifying key moments that could effectively distinguish between positive and negative classes, our method enhanced the ability to predict further into the future. The method proposed in this study demonstrated superior performance to existing methods and proved the feasibility of early prediction for longer time lags.
Improving Conversational Query Rewriting through Generative Coreference Resolution
http://doi.org/10.5626/JOK.2024.51.11.1028
Conversational search enables retrieval of relevant passages for a current turn query by understanding the contextual meaning in a multi-turn dialogue. In conversational search, Conversational Query Reformulation enables utilization of off-the-shelf retrievers by transforming context-dependent queries into self-contained forms. Existing approaches primarily fine-tune pre-trained language models using human-rewritten queries as labels or prompt large language models (LLMs) to address ambiguity inherent in the current turn query, such as ellipsis and coreference. However, our preliminary experimental results indicate that existing models continue to face challenges with coreference resolution. This paper addresses two main research questions: 1) Can a model be trained to distinguish anaphoric mentions that need further clarification? And 2) Can a model be trained to clarify detected coreference mentions into more specified phrases? To investigate these questions, we devised two main components - the detector and the decoder. Our experiments demonstrated that our fine-tuned detector could identify diverse anaphoric phrases within questions, while our fine-tuned decoder could successfully clarify them, ultimately enabling effective coreference resolution for query rewriting. Therefore, we present a novel paradigm, Coreference Aware Conversational Query Reformulation, utilizing these main components.
Proposal of An Intent Classification Method Using Text Augmentation Techniques and Transfer Learning
Huiwon Lee, Sungho Park, Chaewon Lee, Seunghyun Lee, Kangbae Lee
http://doi.org/10.5626/JOK.2024.51.2.141
Intent classification is the first step of task-directed chatbots and is an important phase in performance improvement. However, task-oriented chatbots are limited by a lack of data for specific domains. The purpose of this study is to solve the problem of data limitation by utilizing text augmentation techniques and transfer learning. Previously, studies using transfer learning and text augmentation techniques existed, but it was difficult to find studies applicable to various domains. This study proposes a text augmentation technique and transfer learning method applicable to various domains. For the experiment, less than 10,000, 20,000, and 30,000 data were constructed according to the ratio of actual utterance intentions in 8 domains. As a result of the experiment, although differences existed depending on the domain, it was confirmed that the method proposed in this study was excellent for all 8 domains. It was confirmed that the accuracy for the 8 domains improved by 10%, 3.4%, and 1.9%, respectively on average with the decreasing size of the training data, and the F1-Score improved by 30%, 12%, and 7.5%, respectively on average.
ECG Arrhythmia Classification Model with VAE-based Data Augmentation and CNN
http://doi.org/10.5626/JOK.2023.50.11.947
Due to its convenient accessibility, and crucial importance in arrhythmia diagnosis, ECG data is often considered in predicting heart disease. The MIT-BIH Arrhythmia dataset, which is widely utilized in research focused on arrhythmia analysis, is one of the contributing factors to heart disease. However, the dataset exhibits imbalanced arrhythmia classes due to variations in incidence rate. These imbalanced arrhythmia classes affect the performance of arrhythmia classification. To solve the imbalanced problem, this paper presents four distinct classification methods that utilize augmented data. These different augmentation techniques were compared and assessed alongside the VAE method in terms of classification performance. Furthermore, the CNN and the CNN-LSTM models were compared and analyzed in the context of the classification model. In conclusion, by applying VAE augmentation to train the balanced data and classifying the arrhythmia using the CNN, we achieved an accuracy of 98.9%. These results confirm the superior effectiveness of the proposed model compared to other existing arrhythmia classification models, particularly in terms of the sensitivity.
Time-Series Data Augmentation Based on Adversarial Training
http://doi.org/10.5626/JOK.2023.50.8.671
Recently, time series data are being generated in various industries with advancement of the Internet of Things (IoT). Accordingly, demands for time series forecasting in various industries are increasing. With acquisition of a large amount of time-series data, studies on traditional statistical method based time-series forecasting and deep learning-based forecasting methods have become active and the need for data augmentation techniques has emerged. In this paper, we proposed a novel data augmentation method for time series forecasting based on adversarial training. Unlike conventional adversarial training, the proposed method could fix the hyperparameter about the number of adversarial training iterations and utilize blockwise clipping of perturbations. We carried out various experiments to verify the performance of the proposed method. As a result, we were able to confirm that the proposed method had consistent performance improvement effect on various datasets. In addition, unlike conventional adversarial training, the necessity of blockwise clipping and the hyperparameter value fixing proposed in this paper were also verified through comparative experiments.
Document-level Machine Translation Data Augmentation Using a Cluster Algorithm and NSP
http://doi.org/10.5626/JOK.2023.50.5.401
In recent years, research on document level machine translation has been actively conducted to understand the context of the entire document and perform natural translation. Similar to the sentence-level machine translation model, a large amount of training data is required for training of the document-level machine translation model, but there is great difficulty in building a large amount of document-level parallel corpus. Therefore, in this paper, we propose a data augmentation technique effective for document-level machine translation in order to improve the lack of parallel corpus per document. As a result of the experiment, by applying the data augmentation technique using the cluster algorithm and NSP to the sentence unit parallel corpus without context, the performance of the document-level machine translation is improved by S-BLEU 3.0 and D-BLEU 2.7 compared to that before application of the data augmentation technique.
Improving the Quality of Generating Imbalance Data in GANs through an Exhaustive Contrastive Learning Method
Hyeonjun Shin, Sangbaek Lee, Kyuchul Lee
http://doi.org/10.5626/JOK.2023.50.4.295
As the performance of deep learning algorithms has improved, they are being used as a way to solve various problems in the real world. In the case of data that reflect the real world, imbalance data may occur depending on the frequency of occurrence of events or the difficulty of collection. Data with an inconsistent number of classes that make up the data are called imbalance data, and in particular, it is difficult to learn the minority classes with relatively little data through Deep Learning algorithms. Recently, Generative Adversarial Nets (GANs) have been applied as a method for data augmentation, and self-supervised learning-based pre-learning has been proposed for minority class learning. However, because class information of imbalance data is utilized in the process of learning the Generative Model, the quality of generated data is poor due to poor learning of minority classes. To solve this problem, this paper proposes a similarity-based exhaustive contrast learning method. The proposed method is quantitatively evaluated through the Frechet Inception Distance (FID) and Inception Score (IS). The method proposed in this paper confirmed the performance improvement of the Frechet Inception Distance of 16.32 and the Inception Score of 0.38, as compared to the existing method.
Copy-Paste Based Image Data Augmentation Method Using
http://doi.org/10.5626/JOK.2022.49.12.1056
In the field of computer vision, massive well-annotated image data are essential to achieve good performance of a convolutional neural network (CNN) model. However, in real world applications, gathering massive well-annotated data is a difficult and time-consuming job. Thus, image data augmentation has been continually studied. In this paper, we proposed an image data augmentation method that could generate more diverse image data by combining generative adversarial network (GAN) and copy-paste based augmentation. The proposed method generated not pixel-level or image-level augmentation, but object-level augmentation by cutting off segmentation boundaries(mask) instead of bounding boxes. It then applyied GAN to transform objects.
Utilizing External Knowledge in Natural Language Video Localization
Daneul Kim, Daechul Ahn, Jonghyun Choi
http://doi.org/10.5626/JOK.2022.49.12.1097
State-of-the-art Natural Language Video Localization (NLVL) models mostly use existing labels to train. The use of either full-supervision or weak-supervision needs costly annotations, which are not applicable to the real-world NLVL problems. Thus, in this study, we propose the framework of External Knowledge-based Natural Language Video Localization (EK-NLVL), which leverages the idea of generating the pseudo-supervision based on a captioning model that generates sentences from the given frames and summarizes them to ground the video event. Moreover, we propose data augmentation using the pre-trained multi-modal representation learning model CLIP for visual-aligned sentence filtering to generate pseudo-sentences that could effectively provide better quality augmentation. We also propose a new model, Query-Attentive on Segmentations Network (QAS) which effectively uses external knowledge for the NLVL task. Experiments using the Charades-STA dataset demonstrated the efficacy of our method compared to the existing models.
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