• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• 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
• /
• 제16권2호
• /
• 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.

• 지식경영연구
• /
• 제21권1호
• /
• 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.

• 정보학연구
• /
• 제2권2호
• /
• pp.269-279
• /
• 1999

정보화 사회에서 많은 문서가 전자화 됨에 따라 효율적인 처리를 위해 구조화된 전자 문서 처리가 요구되고 있다. 이에 SGML은 구조화된 정보를 생성하고 교환하기 위한 문서 표준으로써, 이러한 전자 문서를 보여주고 수정하며 새로운 문서를 생성하기에 알맞다. 이에 따라 대량의 구조화된 SGML 문서 정보의 저장, 관리에 관한 연구가 필요하다. 본 논문은 HyTime(Hypermedia Time-based Structuring Language)에서 정의된 GROVE(Graph Representation Of property ValuEs)를 이용하여 데이터 모델링 설계 및 SGML 문서 저장 관리 시스템 설계에 대해 기술한다.

• 정보관리연구
• /
• 제38권1호
• /
• pp.1-19
• /
• 2007

이 연구에서는 최근 검색성능을 향상시키기 위한 전략으로 사용되는 데이터 결합기법을 웹 문서 검색에 적용하고, 실험을 통해 문서표현 방법의 결합이 검색성능에 미치는 영향을 분석하였다. 문서 표현 방법으로는 내용기반 표현, 링크기반 표현,URL 등을 선정하고, 단일 표현 방법에 의한 검색결과와 표현방법의 결합을 통한 검색결과를 비교하였다. 분석결과 다른 문서표현 방법의 결합이 웹 문서의 검색성능을 향상시키지는 못하는 것으로 나타났다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• 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.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2022년도 제34회 한글 및 한국어 정보처리 학술대회
• /
• 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.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 추계종합학술대회
• /
• pp.363-367
• /
• 2002

컴퓨터를 이용한 전자문서처리에 이용되는 기존의 문서편집 시스템에서는 비구조적인 문서구조를 다루게 됨으로써 시스템 내에서 사용되는 수학식의 표현은 이미지나 텍스트 등의 비구조적인 방법에 의해 표현되거나 처리된다. 이렇게 사용된 수학식은 문서의 가독성과 재사용성 그리고 문서의 처리와 교환에 상대적인 불편을 초래하게 된다. 그러므로 이러한 단점을 극복하고 효율적으로 구조적인 문서상에 MathML(Mathematical Markup Language) 수식 구조를 적용시킬 수 있는 문서편집 시스템이 요구된다. 이에 본 논문에서는 MathML을 기반으로 한 수학식의 표현을 구조적으로 처리할 수 있는 MathML 수식 편집이 가능한 XML(eXtensible Markup Language) 기반의 구조적 문서생성을 위한 문서 편집 시스템을 설계 및 구현하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권2호
• /
• 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.

• 정보기술과데이타베이스저널
• /
• 제1권1호
• /
• pp.31-62
• /
• 1994

Information systems for application areas like office automation, customer service or computer aided manufacturing are usually highly interactive and deal with complex document structures composed of multiple media formats. For the realization of these systems, nonstandard database systems, which we call document databases, need to handle different types of coarse-and fine-grained document objects(like full-text documents, graphics and images), hierarchical and non-hierarchical relationships between objects(like composition-links and cross-references using hypertext structures) and document attributes of different types such as formatting/presentation information and access control. In this paper, we present the underlying data model for document databases based on descriptive markup languages that provide mechanisms for specifying the logical structure(or schema) of individual documents stored in the database. We then describe extensions to the data model for supporting notion of composite structures("join" operators for documents) --composition and hyperlinking mechanisms for representing compound documents and inter-linked documents as unique entites separate from their components. Furthermore, due to the interactive nature of the application domains, the database system in conjunction with clients(or browsers) has to support visual navigation and graphical query mechanisms. We describe the functionality of a new user interface paradigm called HyBrow for meeting the above mentioned requirements. The underlying implementation strategy is also discussed.discussed.