• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.45-55
• /
• 2022

Recently, large-scale language models (LPLM) have been shown state-of-the-art performances in various tasks of natural language processing including intent classification. However, fine-tuning LPLM requires much computational cost for training and inference which is not appropriate for dialog system. In this paper, we propose compressed intent classification model for multi-agent in low-resource like CPU. Our method consists of two stages. First, we trained sentence encoder from LPLM then compressed it through knowledge distillation. Second, we trained agent-specific adapter for intent classification. The results of three intent classification datasets show that our method achieved 98% of the accuracy of LPLM with only 21% size of it.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.57-63
• /
• 2021

Spoken language understanding, which aims to understand utterance as naturally as human would, are mostly focused on English language. In this paper, we construct a Korean language dataset for spoken language understanding, which is based on a conversational corpus between reservation system and its user. The domain of conversation is limited to restaurant reservation. There are 7 types of slot tags and 5 types of intent tags in 6857 sentences. When a model proposed in English-based research is trained with our dataset, intent classification accuracy decreased a little, while slot filling F1 score decreased significantly.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.43-44
• /
• 2022

기존 자연어 처리 모델은 문맥 단위 단어 임베딩을 처리하지 못하는 한계점을 가지고 있는 한편 최근 BERT 기반 사전학습 모델들은 문장 단위 임베딩이 가능하고 사전학습을 통해 학습 효율이 비약적으로 개선되었다는 특징이 있다. 본 논문에서는 사전학습 언어 모델들을 이용하여 음식점, 배달전문점 등 음식 업종에서 발생한 고객 발화 의도를 분류하고 모델별 성능을 비교하여 최적의 모델을 제안하고자 한다. 연구결과, 사전학습 모델의 한국어 코퍼스와 Vocab 사이즈가 클수록 고객의 발화 의도를 잘 예측하였다. 한편, 본 연구에서 발화자의 의도를 크게 문의와 요청으로 구분하여 진행하였는데, 문의와 요청의 큰 차이점인 '물음표'를 제거한 후 성능을 비교해본 결과, 물음표가 존재할 때 발화자 의도 예측에 좋은 성능을 보였다. 이를 통해 음식 업종에서 발화자의 의도를 예측하는 시스템을 개발하고 챗봇 시스템 등에 활용한다면, 발화자의 의도에 적합한 서비스를 정확하게 적시에 제공할 수 있을 것으로 기대한다.

• Journal of Information Technology Applications and Management
• /
• v.30 no.4
• /
• pp.11-28
• /
• 2023

This paper proposes a method of integrating ChatGPT with traditional chatbot systems to enhance conversational artificial intelligence(AI) and create more efficient conversational systems. Traditional chatbot systems are primarily based on classification models and are limited to intent classification and simple response generation. In contrast, ChatGPT is a state-of-the-art AI technology for natural language generation, which can generate more natural and fluent conversations. In this paper, we analyze the business service areas that can be integrated with ChatGPT and traditional chatbots, and present methods for conducting conversational scenarios through case studies of service types. Additionally, we suggest ways to integrate ChatGPT with traditional chatbot systems for intent recognition, conversation flow control, and response generation. We provide a practical implementation example of how to integrate ChatGPT with traditional chatbots, making it easier to understand and build integration methods and actively utilize ChatGPT with existing chatbots.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.24 no.1
• /
• pp.26-34
• /
• 2010

"Yifangjijie" is a collection of prescription in Traditional Medicine, which was published in Qing dynasty. In this book, effectiveness of prescriptions 1s described by means of Meridians uniquely compared with any others. Therefore, I tried to pay attention to those explanations and arrange by Meridians and effectiveness of prescriptions. Classification by effectiveness of prescriptions has a few points of emphasis in Meridians and Classification of Meridians by effectiveness of prescriptions has intent in somehow. In this paper, authors will explain those classification.

• International Journal of Computer Science & Network Security
• /
• v.22 no.1
• /
• pp.93-96
• /
• 2022

Natural language processing (NLP) is utilized to understand a natural text. Text analysis systems use natural language algorithms to find the meaning of large amounts of text. Text classification represents a basic task of NLP with a wide range of applications such as topic labeling, sentiment analysis, spam detection, and intent detection. The algorithm can transform user's unstructured thoughts into more structured data. In this work, a text classifier has been developed that uses academic admission and registration texts as input, analyzes its content, and then automatically assigns relevant tags such as admission, graduate school, and registration. In this work, the well-known algorithms support vector machine SVM and K-nearest neighbor (kNN) algorithms are used to develop the above-mentioned classifier. The obtained results showed that the SVM classifier outperformed the kNN classifier with an overall accuracy of 98.9%. in addition, the mean absolute error of SVM was 0.0064 while it was 0.0098 for kNN classifier. Based on the obtained results, the SVM is used to implement the academic text classification in this work.

• Journal of the Korean Society for information Management
• /
• v.40 no.3
• /
• pp.99-118
• /
• 2023

The objective of this study is to identify performance factors in the automatic classification of records by utilizing metadata that contains the contextual information of records. For this study, we collected 97,064 records of original textual information from Korean central administrative agencies in 2022. Various classification algorithms, data selection methods, and feature extraction techniques are applied and compared with the intent to discern the optimal performance-inducing technique. The study results demonstrated that among classification algorithms, Random Forest displayed higher performance, and among feature extraction techniques, the TF method proved to be the most effective. The minimum data quantity of unit tasks had a minimal influence on performance, and the addition of features positively affected performance, while their removal had a discernible negative impact.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.410-413
• /
• 2021

본 논문에서는 분류 모델의 주류로 사용되고 있는 Encoder 기반 사전학습 모델(BERT, ALBERT, ELECTRA)의 내부 Encoder Layer가 하부 Layer에서는 Syntactic한 분석을 진행하고 상부 Layer로 갈수록 Semantic 한 분석을 진행하는 점, Layer가 구성됨에 따라 Semantic 정보가 Syntactic 정보를 개선해 나간다 점에 기반한 기존 연구 결과를 바탕으로 Encoder Layer를 구성함에 따라 어떻게 성능이 변화하는지 측정한다. 그리고 의도 분류를 위한 학습 데이터 셋도 분류하고자 하는 성격에 따라 Syntactic한 구성과 Semantic한 구성을 보인다는 점에 착안하여 ALBERT 및 ELECTRA를 이용한 의도 분류 모델을 구축하고 각 데이터 셋에 맞는 최적의 Encoder Layer 구성을 가지는 모델을 비교한 결과, 두 데이터 셋 간에 다른 Layer 구성을 보이는 점과 기존 모델보다 성능이 향상됨을 확인하였다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.479-484
• /
• 2023

다중 레이블 오픈 의도 분류란 다중 의도 분류와 오픈 의도 분류가 합쳐져 오픈 도메인을 가정하고 진행하는 다중 의도 분류 문제이다. 발화 속에는 여러 의도들이 존재한다. 이때 사전에 정의된 의도 여부만을 판별하는 것이 아니라 사전에 정의되어 있는 의도에 대해서만이라도 어떤 의도인지 분류할 수 있어야 한다. 본 논문에서는 발화 속 의도 정보를 활용하여 다중 레이블 오픈 의도를 분류하는 모델을 제안한다. 먼저, 문장의 의도 개수를 예측한다. 그리고 다중 레이블 의도 분류기를 통해 다중 레이블 의도 분류를 진행하여 의도 정보를 획득한다. 획득한 의도 정보 속 다중 의도 개수와 전체 의도 개수를 비교하여 전체 의도 개수가 더 많다면 오픈 의도가 존재한다고 판단한다. 실험 결과 제안한 방법은 MixATIS의 75% 의도에서 정확도 94.49, F1 97.44, MixSNIPS에서는 정확도 86.92, F1 92.96의 성능을 보여준다.

• The Journal of Korea Robotics Society
• /
• v.14 no.3
• /
• pp.228-235
• /
• 2019

This paper presents a multiple DoFs (degrees-of-freedom) prosthetic forearm and sEMG (surface electromyogram) pattern recognition and motion intent classification of forearm amputee. The developed prosthetic forearm has 9 DoFs hand and single-DoF wrist, and the socket is designed considering wearability. In addition, the pattern recognition based on sEMG is proposed for prosthetic control. Several experiments were conducted to substantiate the performance of the prosthetic forearm. First, the developed prosthetic forearm could perform various motions required for activity of daily living of forearm amputee. It was able to control according to shape and size of the object. Additionally, the amputee was able to perform 'tying up shoe' using the prosthetic forearm. Secondly, pattern recognition and classification experiments using the sEMG signals were performed to find out whether it could classify the motions according to the user's intents. For this purpose, sEMG signals were applied to the multilayer perceptron (MLP) for training and testing. As a result, overall classification accuracy arrived at 99.6% for all participants, and all the postures showed more than 97% accuracy.