Digital Library[ Search Result ]
Multi-Level Attention-Based Generation Model for Long-Term Conversation
Hongjin Kim, Bitna Keum, Jinxia Huang, Ohwoog Kwon, Harksoo Kim
http://doi.org/10.5626/JOK.2025.52.2.117
Research into developing more human-like conversational models is actively underway, utilizing persona memory to generate responses. Many existing studies employ a separate retrieval model to identify relevant personas from memory, which can slow down the overall system and make it cumbersome. Additionally, these studies primarily focused on ability to respond by reflecting a persona well. However, the ability to determine the necessity of referencing a persona should precede this. Therefore, in this paper, we propose a model that does not use a retriever. Instead, the need to reference memory was determined through multi-level attention operations within the generation model itself. If a reference is deemed necessary, the response reflects the relevant persona; Otherwise, the response focuses on the conversational context. Experimental results confirm that our proposed model operates effectively in long-term conversations.
Multi-task Learning Based Re-ranker for External Knowledge Retrieval in Document-grounded Dialogue Systems
http://doi.org/10.5626/JOK.2023.50.7.606
Document-grounded dialogue systems retrieve external passages related to the dialogue and use them to generate an appropriate response to the user"s utterance. However, the retriever based on the dual-encoder architecture records low performance in finding relevant passages, and the re-ranker to complement the retriever is not sufficiently optimized. In this paper, to solve these problems and perform effective external passage retrieval, we propose a re-ranker based on multi-task learning. The proposed model is a cross-encoder structure that simultaneously learns contrastive learning-based ranking, Masked Language Model (MLM), and Posterior Differential Regularization (PDR) in the fine-tuning stage, enhancing language understanding ability and robustness of the model through auxiliary tasks of MLM and PDR. Evaluation results on the Multidoc2dial dataset show that the proposed model outperforms the baseline model in Recall@1, Recall@5, and Recall@10.
CommonAI: Quantitative and Qualitative Analysis for Automatic-generation of Commonsense Reasoning Conversations Suitable for AI
Hyeon Gyu Shin, Hyun Jo You, Young Sook Song
http://doi.org/10.5626/JOK.2023.50.5.407
Human-like common sense reasoning is now considered an essential component for improving the quality of natural language generation for chatbots and conversational agents, However, there is no clear consensus at present about to what extent AI systems require common sense. We discussed common sense requirements for AI chatbots based on quantitative and qualitative analysis of results from two experimental surveys to show differences between gender and age groups and variations according to conversation topics. The contribution of this paper is to refine preferences for chatbot conversations that provide useful information and show an appropriate level of empathy.
Entity Graph Based Dialogue State Tracking Model with Data Collection and Augmentation for Spoken Conversation
http://doi.org/10.5626/JOK.2022.49.10.891
As a part of a task-oriented dialogue system, dialogue state tracking is a task for understanding the dialogue and extracting user’s need in a slot-value form. Recently, Dialogue System Track Challenge (DSTC) 10 Track 2 initiated a challenge to measure the robustness of a dialogue state tracking model in a spoken conversation setting. The released evaluation dataset has three characteristics: new multiple value scenario, three-times more entities, and utterances from automatic speech recognition module. In this paper, to ensure the model’s robust performance, we introduce an extraction-based dialogue state tracking model with entity graph. We also propose to use data collection and template-based data augmentation method. Evaluation results prove that our proposed method improves the performance of the extraction-based dialogue state tracking model by 1.7% of JGA and 0.57% of slot accuracy compared to baseline model.
Alleviation of Generic Responses by Adjusting N-gram Usage in Neural Chit-chat Dialogue Systems
JaeYoung Oh, WonKee Lee, Jeesoo Bang, Jaehun Shin, Jong-Hyeok Lee
http://doi.org/10.5626/JOK.2022.49.1.60
Chit-chat dialogue systems, the systems for unstructured conversations between humans and computer, aim to generate meaningful and diverse responses. However, training methods based on the maximum likelihood estimation have been reported to generate too many generic responses by the model; thus, reducing the interest in these systems. Recently, a new training method using unlikelihood training was proposed to generate diverse responses by penalizing the overuse of each vocab. However, it has a limitation that it only considers the usage of a token when penalizing each word, and does not consider in what context each token is used. Therefore, we propose a method by extending this work, which is penalizing the overuse of each n-gram. This method has the advantage of using information about the surrounding context in n-gram to penalize each token.
Query Intent Detection for Medical Advice: Training Data Construction and Intent Classification
Tae-Hoon Lee, Young-Min Kim, Eunji Jeong, Seon-Ok Na
http://doi.org/10.5626/JOK.2021.48.8.878
In most task-oriented dialogue systems, intent detection and named entity recognition need to precede. This paper deals with the query intent detection to construct a dialogue system for medical advice. We start from the appropriate intent categories for the final goal. We also describe in detail the data collection, training data construction, and the guidelines for the manual annotation. BERT-based classification model has been used for query intent detection. KorBERT, a Korean version of BERT has been also tested for detection. To verify that the DNN-based models outperform the traditional machine learning methods even for a mid-sized dataset, we also tested SVM, which produces a good result in general for such dataset. The F1 scores of SVM, BERT, and KorBERT are 69%, 78%, and 84% respectively. For future work, we will try to increase intent detection performance through dataset improvement.
Analyzing and Solving GuessWhat?!
Sang-Woo Lee, Cheolho Han, Yujung Heo, Wooyoung Kang, Jaehyun Jun, Byoung-Tak Zhang
http://doi.org/10.5626/JOK.2018.45.1.30
GuessWhat?! is a game in which two machine players, composed of questioner and answerer, ask and answer yes-no-N/A questions about the object hidden for the answerer in the image, and the questioner chooses the correct object. GuessWhat?! has received much attention in the field of deep learning and artificial intelligence as a testbed for cutting-edge research on the interplay of computer vision and dialogue systems. In this study, we discuss the objective function and characteristics of the GuessWhat?! game. In addition, we propose a simple solver for GuessWhat?! using a simple rule-based algorithm. Although a human needs four or five questions on average to solve this problem, the proposed method outperforms state-of-the-art deep learning methods using only two questions, and exceeds human performance using five questions.
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