• Korean Journal of Cognitive Science
• /
• v.20 no.4
• /
• pp.421-437
• /
• 2009

A chatting system is a computer program that simulates conversations between a human and a computer using natural language. In this paper, we propose a statistical model to generate natural chatting sentences when keywords and speech acts are input. The proposed model first finds Eojeols (Korean spacing units) including input keywords from a corpus, and generate sentence candidates by using appearance information and syntactic information of Eojeols surrounding the found Eojeols. Then, the proposed model selects one among the sentence candidates by using a language model based on speech act information, co-occurrence information between Eojeols, and syntactic information of each Eojeol. In the experiment, the proposed model showed the better correct sentence generation rate of 86.2% than a previous conventional model based on a simple language model.

• ETRI Journal
• /
• v.39 no.4
• /
• pp.455-466
• /
• 2017

This study focuses on a method for sequential data augmentation in order to alleviate data sparseness problems. Specifically, we present corpus expansion techniques for enhancing the coverage of a language model. Recent recurrent neural network studies show that a seq2seq model can be applied for addressing language generation issues; it has the ability to generate new sentences from given input sentences. We present a method of corpus expansion using a sentence-chain based seq2seq model. For training the seq2seq model, sentence chains are used as triples. The first two sentences in a triple are used for the encoder of the seq2seq model, while the last sentence becomes a target sequence for the decoder. Using only internal resources, evaluation results show an improvement of approximately 7.6% relative perplexity over a baseline language model of Korean text. Additionally, from a comparison with a previous study, the sentence chain approach reduces the size of the training data by 38.4% while generating 1.4-times the number of n-grams with superior performance for English text.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.5
• /
• pp.592-601
• /
• 2016

The recurrent neural network (RNN) is a deep learning model which is suitable to sequential or length-variable data. The Long Short-Term Memory (LSTM) mitigates the vanishing gradient problem of RNNs so that LSTM can maintain the long-term dependency among the constituents of the given input sequence. In this paper, we propose a LSTM based language model which can predict following words of a given incomplete sentence to generate a complete sentence. To evaluate our method, we trained our model using multiple Korean corpora then generated the incomplete part of Korean sentences. The result shows that our language model was able to generate the fluent Korean sentences. We also show that the word based model generated better sentences compared to the other settings.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.215-219
• /
• 2020

현재 한글 언어학 영역에서는 많은 언어 분석 연구가 수행되었다. 또한 소프트웨어공학의 요구공학 영역에서는 명료한 요구사항 정의와 분석이 필요하고, 비정형화된 요구사항 명세서로부터 테스트 케이스 추출이 매우 중요한 이슈이다. 즉, 자연어 기반의 요구사항 명세서로부터 원인-결과 그래프(Cause-Effect Graph)를 통한 의사 결정 테이블(Decision Table) 기반 테스트케이스(Test Case)를 자동 생성하는 방법이 거의 없다. 이런 문제를 해결하기 위해 '한글 언어 의미 분석 기법'을 '요구공학 영역'에 적용하는 방법이 필요하다. 본 논문은 비정형화된 요구사항으로부터 테스트케이스 생성하는 과정의 중간 단계인 요구사항에서 문장 의미 모델(Sentence Semantic Model)을 자동 생성하는 방법을 제안 한다. 이는 요구사항으로부터 생성된 원인-결과 그래프의 정확성을 검증할 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2718-2731
• /
• 2023

This paper presents a method of using syntax and shallow semantic analysis for Vietnamese question generation (QG). Specifically, our proposed technique concentrates on investigating both the syntactic and shallow semantic structure of each sentence. The main goal of our method is to generate questions from a single sentence. These generated questions are known as factoid questions which require short, fact-based answers. In general, syntax-based analysis is one of the most popular approaches within the QG field, but it requires linguistic expert knowledge as well as a deep understanding of syntax rules in the Vietnamese language. It is thus considered a high-cost and inefficient solution due to the requirement of significant human effort to achieve qualified syntax rules. To deal with this problem, we collected the syntax rules in Vietnamese from a Vietnamese language textbook. Moreover, we also used different natural language processing (NLP) techniques to analyze Vietnamese shallow syntax and semantics for the QG task. These techniques include: sentence segmentation, word segmentation, part of speech, chunking, dependency parsing, and named entity recognition. We used human evaluation to assess the credibility of our model, which means we manually generated questions from the corpus, and then compared them with the generated questions. The empirical evidence demonstrates that our proposed technique has significant performance, in which the generated questions are very similar to those which are created by humans.

• Journal of the Korean Society for information Management
• /
• v.18 no.3
• /
• pp.159-178
• /
• 2001

This paper presents an automatic text summarization model which selects representative sentences from sentence clusters to create a summary. Summary generation experiments were performed on two sets of test documents after learning the optimum environment from a training set. Centroid clustering method turned out to be the most effective in clustering sentences, and sentence weight was found more effective than the similarity value between sentence and cluster centroid vectors in selecting a representative sentence from each cluster. The result of experiments also proves that inverse sentence weight as well as title word weight for terms and location weight for sentences are effective in improving the performance of summarization.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.17-18
• /
• 2017

자연어 처리 분야에서 대화문 생성, 질의응답 등과 같은 문장생성과 관련된 연구가 꾸준히 진행되고 있다. 본 논문에서는 기존 순환신경망 모델에 Neural Attention을 추가하여 주제 정보를 어느 정도 포함시킬지 결정한 뒤 다음 문장을 생성할 때 사용하는 모델을 제안한다. 이는 기존 문장과 다음 문장의 확률 정보를 사용할 뿐만 아니라 주제 정보를 추가하여 문맥적인 의미를 넣을 수 있기 때문에, 더욱 연관성 있는 문장을 생성할 수 있게 도와준다. 이 모델은 적절한 다음 문장을 생성할 뿐만 아니라 추가적으로 어떤 단어가 다음 문장을 생성함에 있어 주제문장에 더 민감하게 반응하는지 확인할 수 있다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.15-30
• /
• 2023

Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.81-88
• /
• 2024

Despite the rapid growth of the generative AI market and significant interest from domestic companies and institutions, concerns about the provision of inaccurate information and potential information leaks have emerged as major factors hindering the adoption of generative AI. To address these issues, this paper designs and implements a question-answering system based on the Retrieval-Augmented Generation (RAG) architecture. The proposed method constructs a knowledge database using Korean sentence embeddings and retrieves information relevant to queries through optimized searches, which is then provided to the generative language model. Additionally, it allows users to directly manage the knowledge database to efficiently update changing business information, and it is designed to operate in a private network to reduce the risk of corporate confidential information leakage. This study aims to serve as a useful reference for domestic companies seeking to adopt and utilize generative AI.