• 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.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.599-612
• /
• 2022

This study focuses on improving a word embedding model to enhance the performance of downstream tasks, such as those of dialog systems. To improve traditional word embedding models, such as skip-gram, it is critical to refine the word features and expand the context model. In this paper, we approach the word model from the perspective of subword embedding and attempt to extend the context model by integrating various sentence models. Our proposed sentence model is a subword-based skip-thought model that integrates self-attention and relative position encoding techniques. We also propose a clustering-based dialog model for downstream task verification and evaluate its relationship with the sentence-model-based subword embedding technique. The proposed subword embedding method produces better results than previous methods in evaluating word and sentence similarity. In addition, the downstream task verification, a clustering-based dialog system, demonstrates an improvement of up to 4.86% over the results of FastText in previous research.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.149-154
• /
• 2006

The main purpose of document summarization is to reduce the complexity of documents that are consisted of sub-themes. Also it is to create summarization which includes the sub-themes. This paper proposes a summarization system which could extract any salient sentences in accordance with sub-themes by using graph division. A document can be represented in graphs by using chosen representative terms through term relativity analysis based on co-occurrence information. This graph, then, is subdivided to represent sub-themes through connected information. The divided graphs are types of sentence clustering which shows a close relationship. When salient sentences are extracted from the divided graphs, summarization consisted of core elements of sentences from the sub-themes can be produced. As a result, the summarization quality will be improved.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.297-304
• /
• 2010

Clustering method which based on sentence type or document genre is a technique used to improve translation quality of SMT(statistical machine translation) by domain-specific translation. But there is no previous research using sentence type and document genre information simultaneously. In this paper, we suggest an integrated clustering method that classifying sentence type by syntactic structure similarity and document genre by word similarity information. We interpolated domain-specific models from clusters with general models to improve translation quality of SMT system. Kernel function and cosine measures are applied to calculate structural similarity and word similarity. With these similarities, we used machine learning algorithms similar to K-means to clustering. In Japanese-English patent translation corpus, we got 2.5% point relative improvements of translation quality at optimal case.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.12
• /
• pp.2607-2613
• /
• 2012

The results of inherent knowledge based generic summarization are influenced by the composition of sentence in document set. In order to resolve the problem, this papser propses a new generic document summarization which uses clustering of semantic feature of document and coherence of document cluster. The proposed method clusters sentences using semantic feature deriving from NMF(non-negative matrix factorization), which it can classify document topic group because inherent structure of document are well represented by the sentence cluster. In addition, the method can improve the quality of summarization because the importance sentences are extracted by using coherence of sentence cluster and the cluster refinement by re-cluster. The experimental results demonstrate appling the proposed method to generic summarization achieves better performance than generic document summarization methods.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.127-130
• /
• 2003

This paper describes an efficient method for unsupervised speaker adaptation. This method is based on selecting a subset of speakers who are acoustically close to a test speaker, and calculating adapted model parameters according to the previously stored sufficient HMM statistics of the selected speakers' data. In this method, only a few unsupervised test speaker's data are required for the adaptation. Also, by using the sufficient HMM statistics of the selected speakers' data, a quick adaptation can be done. Compared with a pre-clustering method, the proposed method can obtain a more optimal speaker cluster because the clustering result is determined according to test speaker's data on-line. Experiment results show that the proposed method attains better improvement than MLLR from the speaker independent model. Moreover the proposed method utilizes only one unsupervised sentence utterance, while MLLR usually utilizes more than ten supervised sentence utterances.

• Journal of the Korean Society for information Management
• /
• v.21 no.3
• /
• pp.289-303
• /
• 2004

This experimental study proposes a multi-document summarization method that produces optimal summaries in which users can find answers to their queries. In order to identify the most effective method for this purpose, the performance of the three summarization methods were compared. The investigated methods are sentence clustering, passage extraction through spreading activation, and clustering-passage extraction hybrid methods. The effectiveness of each summarizing method was evaluated by two criteria used to measure the accuracy and the redundancy of a summary. The passage extraction method using the sequential bnb search algorithm proved to be most effective in summarizing multiple documents with regard to summarization precision. This study proposes the passage extraction method as the optimal multi-document summarization method.

• MALSORI
• /
• no.66
• /
• pp.87-103
• /
• 2008

We describe a new active learning method in conditional random fields (CRFs) framework for keyphrase extraction. To save elaboration in annotation, we use diversity and representative measure. We select high diversity training candidates by sentence confidence value. We also select high representative candidates by clustering the part-of-speech patterns of contexts. In the experiments using dialog corpus, our method achieves 86.80% and saves 88% training corpus compared with those of supervised method. From the results of experiment, we can see that the proposed method shows improved performance over the previous methods. Additionally, the proposed method can be applied to other applications easily since its implementation is independent on applications.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.195-204
• /
• 2023

In this study, prompt engineering that improves prompts was explored to improve the performance of teaching and learning materials recommendations using generative artificial intelligence such as GPT and Stable Diffusion. Picture materials were used as the types of teaching and learning materials. To explore the impact of the prompt composition, a Zero-Shot prompt, a prompt containing learning target grade information, a prompt containing learning goals, and a prompt containing both learning target grades and learning goals were designed to collect responses. The collected responses were embedded using Sentence Transformers, dimensionalized to t-SNE, and visualized, and then the relationship between prompts and responses was explored. In addition, each response was clustered using the k-means clustering algorithm, then the adjacent value of the widest cluster was selected as a representative value, imaged using Stable Diffusion, and evaluated by 30 elementary school teachers according to the criteria for evaluating teaching and learning materials. Thirty teachers judged that three of the four picture materials recommended were of educational value, and two of them could be used for actual classes. The prompt that recommended the most valuable picture material appeared as a prompt containing both the target grade and the learning goal.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.172-174
• /
• 1999

본 논문에서는 카운셀링을 원하는 사용자가 카운셀러와 전자메일을 통해 상담을 원할 때 사용자의 상담 내용에 근거하여 유사한 사례를 검색해 주는 시스템을 제안한다. 제안방법은 문서의 계층적 클러스터링과 용어 적합성 피드백을 상담 사례 검색 시스템에 적용시켜, 상담사례에 나타나는 단어의 출현 빈도와 유사도를 통해 트리 구조를 형성하고, 이 트리 구조를 통한 하향 탐색을 수행한다. 하향 탐색을 하는 도중 노드의 매칭함수의 값이 서로 유사하여 노드 선택이 어려울 경우, 사용자에게 질의를 통해 용어를 제시하고, 사용자의 피드백을 통해 입력된 사연 내용의 가중치를 개선하여 내용에 가장 부합되는 문서를 탐색한다.