• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.413-416
• /
• 2001

인터넷 문서에서 구조정보의 대표적인 예라 할 수 있는 표(table)는 의미있는 정보를 가지고 있는 경우가 많다. 하지만 인터넷상의 표는 여러 가지 형태이며, 이것에 맞게 표를 효과적으로 parsing하는 방법이 필요하다. 이렇게 parsing한 표의 정보를 이용하여, 인터넷 문서, 특히 전자상거래 문서에 있는 표를 표준화한 틀에 따라 개념화하여, 의미있는 정보를 추출해 낼 수 있다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.7
• /
• pp.571-579
• /
• 2009

A left-comer and look-ahead chart parsing algorithm suppresses the generation of meaningless intermediate structures, and thus, gains parsing speed-ups. However, the algorithm requires additional costs to maintain left-comer and look-ahead information throughout the parsing process. Albeit the additional costs, previous research shows that significant parsing speed-ups have been achieved for large-sized context-free grammars. In this paper, we perform similar experiments with a small-sized grammar. We still get parsing speed-ups, but relatively low. We also find that left-comer information has rather negative effects on parsing speed-ups.

• Korean Journal of Cognitive Science
• /
• v.15 no.1
• /
• pp.25-33
• /
• 2004

This paper discusses two problems with LR parsing with regard to constructing parsing tables with feature-based grammars. First, we show that traditional LR parsing methods suffer from nontermination and nondeterminism problems when they are applied to feature-based grammars. We then present an LR method for feature-based grammars that avoids both nontermination and nondetermisim by making use of partial information of a feature structure. Second, we describe the problem of adapting LR parsing to feature-based grammars with schematic rules (i.e., rules that do not contain enough information to construct parsing tables). To remedy this problem, we propose a rule inference algorithm which instantiates underspecified rules into more specified ones containing enough information.

• Convergence Security Journal
• /
• v.5 no.4
• /
• pp.19-25
• /
• 2005

Threaded Tree is the data structure that can express parse stack as well as parse tree with LR parsing table. $Larchev\^{e}que$ makes Threaded Tree and Incremental Parsing with stack. This paper suggests the algorithm consisting of changed threaded tree without stack in order to reduce reparsing node and parsing speed. Also, it suggests incremental parsing algorithm to get rid of the reparsing process in node.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2003.11a
• /
• pp.51-57
• /
• 2003

In operating distributed systems, proactive management is one of the major concerns for better quality of service and future capacity planning. In order to handle this management problem effectively, it is necessary to analyze performances of the distributed system and events generated by components in the system. This paper provides a rule-based event parsing engine for proactive management. Our event parsing engine uses object hooking-based and event-token approaches. The object hooking-based approach prepares new conditions and actions in Java classes and allows dynamically exchange them as hook objects in run time. The event-token approach allows the event parsing engine consider a proper sequence and relationship among events as an event token to trigger an action. We analyze the performance of our event parsing engine with two different implementations of rule structure; one is table-based and the other is tree-based.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.93-102
• /
• 2022

Dependency parsing is a decision problem of the syntactic relation between words in a sentence. Recently, deep learning models are used for dependency parsing based on the word representations in a continuous vector space. However, it causes a mislabeled tagging problem for the proper nouns that rarely appear in the training corpus because it is difficult to express out-of-vocabulary (OOV) words in a continuous vector space. To solve the OOV problem in dependency parsing, we explored the proper noun embedding method according to the embedding unit. Before representing words in a continuous vector space, we replace the proper nouns with a special token and train them for the contextual features by using the multi-layer bidirectional LSTM. Two models of the syllable-based and morpheme-based unit are proposed for proper noun embedding and the performance of the dependency parsing is more improved in the ensemble model than each syllable and morpheme embedding model. The experimental results showed that our ensemble model improved 1.69%p in UAS and 2.17%p in LAS than the same arc-eager approach-based Malt parser.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.524-543
• /
• 2022

Correct facade image parsing is essential to the semantic understanding of outdoor scenes. Unfortunately, there are often various occlusions in front of buildings, which fails many existing methods. In this paper, we propose an end-to-end deep network for facade parsing with occlusions. The network learns to decompose an input image into visible and invisible parts by occlusion reasoning. Then, a context aggregation module is proposed to collect nonlocal cues for semantic segmentation of the visible part. In addition, considering the regularity of man-made buildings, a repetitive pattern completion branch is designed to infer the contents in the invisible regions by referring to the visible part. Finally, the parsing map of the input facade image is generated by fusing the results of the visible and invisible results. Experiments on both synthetic and real datasets demonstrate that the proposed method outperforms state-of-the-art methods in parsing facades with occlusions. Moreover, we applied our method in applications of image inpainting and 3D semantic modeling.

• Journal of KIISE
• /
• v.44 no.8
• /
• pp.822-831
• /
• 2017

In this paper, we propose a Korean dependency parsing model using multi-task learning based pointer networks. Multi-task learning is a method that can be used to improve the performance by learning two or more problems at the same time. In this paper, we perform dependency parsing by using pointer networks based on this method and simultaneously obtaining the dependency relation and dependency label information of the words. We define five input criteria to perform pointer networks based on multi-task learning of morpheme in dependency parsing of a word. We apply a fine-tuning method to further improve the performance of the dependency parsing proposed in this paper. The results of our experiment show that the proposed model has better UAS 91.79% and LAS 89.48% than conventional Korean dependency parsing.

• Journal of KIISE:Software and Applications
• /
• v.37 no.11
• /
• pp.845-850
• /
• 2010

Incremental parsing has been developed to reuse the parse result of the original string during the parsing of a new string. The previous incremental LL(1) parsing methods precomputed the reusable point information before parsing and used it during parsing. This paper proposes an efficient reusable point computation by factoring the common part of the computation. The common symbol storing method and the distance storing method were previously suggested to find the reusable point, and by combining the methods, this paper gives the storing method of the distance to common symbols. Based on it, an efficient incremental LL(1) parser is constructed.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.255-258
• /
• 2014

본 논문에서는 semantic parsing과 사전 정의된 어휘-의미 패턴 질의 템플릿 방법론을 결합하여 자연어 질의로부터 RDF 지식베이스에 질의하기 위한 SPARQL 쿼리를 생성하는 방법을 제안한다. semantic parsing 접근법은 문장의 표현과 분리된 형식적 의미표현만을 포착해내므로, paraphrase 혹은 의미 변화와 무관한 어순의 변화에 강인하지만, 일부 자연어 질의문장에는 단순한 의미 및 구조를 갖는 문장도 적합한 형식적 의미표현을 생성하지 못하는 단점이 있다. 따라서 이 연구에서는 이러한 단순한 문장에 있어서는 사전 정의된 질의 템플릿을 사용하여 적합한 쿼리를 생성하되, 적합한 템플릿을 선택하는데 있어 해당 질의문장의 어휘-의미적 유형을 포착하고 해당 정보를 이용하는 방법을 이용하였으며 이를 통해 주 방법론의 약점을 보완하는 제한적인 효과를 얻을 수 있었다.