• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.254-276
• /
• 2019

Since the amount of information on the internet is growing rapidly, it is not easy for a user to find relevant information for his/her query. To tackle this issue, the researchers are paying much attention to Document Summarization. The key point in any successful document summarizer is a good document representation. The traditional approaches based on word overlapping mostly fail to produce that kind of representation. Word embedding has shown good performance allowing words to match on a semantic level. Naively concatenating word embeddings makes common words dominant which in turn diminish the representation quality. In this paper, we employ word embeddings to improve the weighting schemes for calculating the Latent Semantic Analysis input matrix. Two embedding-based weighting schemes are proposed and then combined to calculate the values of this matrix. They are modified versions of the augment weight and the entropy frequency that combine the strength of traditional weighting schemes and word embedding. The proposed approach is evaluated on three English datasets, DUC 2002, DUC 2004 and Multilingual 2015 Single-document Summarization. Experimental results on the three datasets show that the proposed model achieved competitive performance compared to the state-of-the-art leading to a conclusion that it provides a better document representation and a better document summary as a result.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.277-300
• /
• 2020

This paper presents a method for clustering short text documents, such as news headlines, social media statuses, or instant messages. Due to the characteristics of these documents, which are usually short and sparse, an appropriate technique is required to discover hidden knowledge. The objective of this paper is to identify the combination of document representation, document distance, and document clustering that yields the best clustering quality. Document representations are expanded by external knowledge sources represented by a Distributed Representation. To cluster documents, a K-means partitioning-based clustering technique is applied, where the similarities of documents are measured by word mover's distance. To validate the effectiveness of the proposed method, experiments were conducted to compare the clustering quality against several leading methods. The proposed method produced clusters of documents that resulted in higher precision, recall, F1-score, and adjusted Rand index for both real-world and standard data sets. Furthermore, manual inspection of the clustering results was conducted to observe the efficacy of the proposed method. The topics of each document cluster are undoubtedly reflected by members in the cluster.

• Knowledge Management Research
• /
• v.21 no.1
• /
• pp.99-116
• /
• 2020

Text is the most widely used means of exchanging or expressing knowledge and information in the real world. Recently, researches on structuring unstructured text data for text analysis have been actively performed. One of the most representative document embedding method (i.e. doc2Vec) generates a single vector for each document using the whole corpus included in the document. This causes a limitation that the document vector is affected by not only core words but also other miscellaneous words. Additionally, the traditional document embedding algorithms map each document into only one vector. Therefore, it is not easy to represent a complex document with interdisciplinary subjects into a single vector properly by the traditional approach. In this paper, we introduce a multi-vector document embedding method to overcome these limitations of the traditional document embedding methods. After introducing the previous study on multi-vector document embedding, we visually analyze the effects of the multi-vector document embedding method. Firstly, the new method vectorizes the document using only predefined keywords instead of the entire words. Secondly, the new method decomposes various subjects included in the document and generates multiple vectors for each document. The experiments for about three thousands of academic papers revealed that the single vector-based traditional approach cannot properly map complex documents because of interference among subjects in each vector. With the multi-vector based method, we ascertained that the information and knowledge in complex documents can be represented more accurately by eliminating the interference among subjects.

• The Journal of Information Technology
• /
• v.2 no.2
• /
• pp.269-279
• /
• 1999

SGML(Standard Generalized Markup Language) is proper to view, modify and create new electronic document as documentation standard to create and interchange the structured document information. Accordingly, a study on efficient storage and management of very large structured SGML document information is need. This paper proposes design of data modeling based on GROVE(Graph Representation Of property ValuEs) defined in HyTime(Hypermedia Time-based Structuring Language) and describes design of SGML document storage management system.

• Journal of Information Management
• /
• v.38 no.1
• /
• pp.1-19
• /
• 2007

This study investigates the effect of data fusion on the retrieval effectiveness by performing an experiment combining multiple representations of Web documents. The types of document representation combined in the study include content terms, links, anchor text, and URL. The experimental results showed that the data fusion technique combining document representation methods in Web environment did not bring any significant improvement in retrieval effectiveness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2178-2198
• /
• 2024

Graph-based document models have good capabilities to reveal inter-dependencies among unstructured text data. Natural language processing (NLP) systems that use such models as an intermediate representation have shown good performance. This paper proposes a novel fuzzy graph-based document model and to demonstrate its effectiveness by applying fuzzy logic tools for text summarization. The proposed system accepts a text document as input and identifies some of its sentence level features, namely sentence position, sentence length, numerical data, thematic word, proper noun, title feature, upper case feature, and sentence similarity. The fuzzy membership value of each feature is computed from the sentences. We also propose a novel algorithm to construct the fuzzy graph as an intermediate representation of the input document. The Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metric is used to evaluate the model. The evaluation based on different quality metrics was also performed to verify the effectiveness of the model. The ANOVA test confirms the hypothesis that the proposed model improves the summarizer performance by 10% when compared with the state-of-the-art summarizers employing alternate intermediate representations for the input text.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4275-4291
• /
• 2021

With the unprecedented growth of textual information on the Internet, an efficient automatic summarization system has become an urgent need. Recently, the neural network models based on the encoder-decoder with an attention mechanism have demonstrated powerful capabilities in the sentence summarization task. However, for paragraphs or longer document summarization, these models fail to mine the core information in the input text, which leads to information loss and repetitions. In this paper, we propose an abstractive document summarization method by applying guidance signals of key sentences to the encoder based on the hierarchical encoder-decoder architecture, denoted as KI-HABS. Specifically, we first train an extractor to extract key sentences in the input document by the hierarchical bidirectional GRU. Then, we encode the key sentences to the key information representation in the sentence level. Finally, we adopt key information representation guided selective encoding strategies to filter source information, which establishes a connection between the key sentences and the document. We use the CNN/Daily Mail and Gigaword datasets to evaluate our model. The experimental results demonstrate that our method generates more informative and concise summaries, achieving better performance than the competitive models.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.135-140
• /
• 2022

최근 Document Retrieval을 비롯한 대부분의 자연어처리 분야에서는 BERT와 같이 self-attention을 기반으로 한 사전훈련 모델을 활용하여 SOTA(state-of-the-art)를 이루고 있다. 그러나 self-attention 메커니즘은 입력 텍스트 길이의 제곱에 비례하여 계산 복잡도가 증가하기 때문에, 해당 모델들은 선천적으로 입력 텍스트의 길이가 제한되는 한계점을 지닌다. Document Retrieval 분야에서는, 문서를 특정 토큰 길이 단위의 문단으로 나누어 각 문단의 유사 점수 또는 표현 벡터를 추출한 후 집계함으로서 길이 제한 문제를 해결하는 방법론이 하나의 주류를 이루고 있다. 그러나 논문, 특허와 같이 섹션 형식(초록, 결론 등)을 갖는 문서의 경우, 섹션 유형에 따라 고유한 정보 특성을 지닌다. 따라서 문서를 단순히 특정 길이의 문단으로 나누어 학습하는 PARADE와 같은 기존 방법론은 각 섹션이 지닌 특성을 반영하지 못한다는 한계점을 지닌다. 본 논문에서는 섹션 유형에 대한 정보를 포함하는 문단 표현을 학습한 후, 트랜스포머 인코더를 사용하여 집계함으로서, 결과적으로 섹션의 특징과 상호 정보를 학습할 수 있도록 하는 SERADE 모델을 제안하고자 한다. 실험 결과, PARADE-Transformer 모델과 비교하여 평균 3.8%의 성능 향상을 기록하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.363-367
• /
• 2002

Represent of mathematical formula used within system handling document that is nonstructural in existent document editing system that is used in electron document processing that use computer is represented or processed by method that is nonstructural of image or text or etc. Such mathematical formular causes relative inconvenience to readablility and reusability of document and processing and exchange of document. Therefore, document editing system is required that can overcome such nonadvantage and apply MathML mathematical formula structure on efficiently structural document. Therefore, designed and implemented that document editing system for structural document creation of XML base that can mathematical formular editing of MathML base in this paper.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.2
• /
• pp.129-134
• /
• 2004

XML is the new universal format for structured documents and data on the World Wide Web. As the Web becomes a major means of disseminating and sharing information and as the amount of XML data increases substantially, there are increased needs to manage and design such XML document in a novel yet efficient way. Moreover a demand of XML Schema(W3C XML Schema Spec.) that verifies XML document becomes increasing recently. However, XML Schema has a weak point for design because of its complication despite of various data and abundant expressiveness. Thus, it is difficult to design a complex document reflecting the usability, global and local facility and ability of expansion. This paper shows a simple way of modeling for XML document using a fundamental means for database design, the Entity-Relationship model. The design from the Entity-Relationship model to XML Schema can not be directly on account of discordance between the two models. So we present some algorithms to generate XML Schema from the Entity-Relationship model. The algorithms produce XML Schema codes using a hierarchical view representation. An important objective of this modeling is to preserve XML Schema's object-oriented concepts such as reusability, global and local ability. In addition to, implementation procedure and evaluation of the proposed design method are described.