• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.97-98
• /
• 2018

최근 딥러닝 기술의 발전으로 영상 분류 및 영상 내 객체 검출뿐만 아니라 CNN 기반의 segmentation 기술도 개발되어 다른 요소까지 포함한 직사각형 영역의 검출 영역이 아닌 경계까지 고려한 분리가 가능하게 되었다. 더불어 사람 영역을 신체부위나 의류 부분과 같은 세부 영역으로 나누어 분리하는 human parsing 기술까지 연구되고 있다. Human parsing은 의류스타일 분석 및 검색, 사람의 행동 인식 및 추적과 같은 분야에도 응용될 수 있다. 본 논문에서는 Spatial pyramid pooling layer를 이용하여 영상 전체에 대한 공간적 분포 및 특성 정보를 고려한 human parsing 기법을 제안한다. Look into person(LIP) dataset을 이용하여 기존의 다른 segmentation 및 human parsing 기법과 제안하는 기법을 비교하여 제안하는 기법의 human parsing 결과가 보다 정교한 분리가 가능한 것을 확인하였다.

• 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.

• 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.

• 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.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.678-681
• /
• 2018

Dependency parsing is an important task in natural language processing whose results are used in many downstream tasks such as machine translation, information retrieval, relation extraction, question answering and many others. Most of the dependency parsing literature focuses on using end-to-end and sequence-to-sequence neural architectures as the core of the system. One such system, namely Biaffine dependency parser is explored in the current paper for effective dependency parsing of Korean language.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2002.02a
• /
• pp.1-1
• /
• 2002

This talk provides an overview of current work in my research group on the syntactic annotation of the T bingen corpus of spoken German and of the German Reference Corpus (Deutsches Referenzkorpus: DEREKO) of written texts. Morpho-syntactic and syntactic annotation as well as annotation of function-argument structure for these corpora is performed automatically by a hybrid architecture that combines robust symbolic parsing with finite-state methods ("chunk parsing" in the sense Abney) with memory-based parsing (in the sense of Daelemans). The resulting robust annotations can be used by theoretical linguists, who lire interested in large-scale, empirical data, and by computational linguists, who are in need of training material for a wide range of language technology applications. To aid retrieval of annotated trees from the treebank, a query tool VIQTORYA with a graphical user interface and a logic-based query language has been developed. VIQTORYA allows users to query the treebanks for linguistic structures at the word level, at the level of individual phrases, and at the clausal level.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.4
• /
• pp.96-101
• /
• 2010

The core study of semantic web is the efficiency of ontology parsing. The ontology parsing and inference is based on the significant information retrieval which is the ultimate purpose of semantic web. However, most existing ontology writing tools were not processing the efficient ontology parsing. Therefore, we design the two steps ontology parser for extracting the all facts, are included in the ontology, more fast in this study. In the first step, the token extractor collects the all tokens of ontology and the triple extractor extracts the statements in the collected tokens. In conclusion, we confirm that which is designed in this study, processes the ontology parsing more faster than the existing ontology parsers.

• Annual Conference on Human and Language Technology
• /
• 1994.11a
• /
• pp.426-433
• /
• 1994

본 논문에서는 트리의 점증적인 합성에 의하여 파싱을 진행시켜 나가는 파싱 방법을 소개하며 이의 한국어 파싱에의 응용을 살펴 본다. 이와 같은 트리 합성 파싱(tree combining parsing)을 지원하기 위한 문법인 트리 합성 문법(Tree Combining Grammar)을 소개한다. 우리는 먼저 문맥 자유 문법을 작성한 후 이로부터 자동적인 변환에 의하여 트리 합성 문법을 얻는 과정을 취한다. 따라서 트리 합성 파싱은 일종의 문맥 자유 파싱(context-free parsing)으로 볼 수 있으나 점증성(incremental), 하향성(top-down), 상향성(bottom-up), 유연성(flexible) 등과 같은 장점을 갖고 있다. 트리 합성 파싱의 유연성을 기반으로 하여 부분 자유 어순, 중심어 후행성과 같은 특성을 가진 한국어를 효과적으로 파싱할 수 있도록 트리 합성 파싱을 확장하는 방법을 살펴본다.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1996.02a
• /
• pp.363-372
• /
• 1996

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.71-75
• /
• 2024

This research focuses on processing unstructured data efficiently, containing various formulas in document processing and management regarding the terms and rules of domestic insurance documents using text mining techniques. Through parsing and compilation technology, document context, content, constants, and variables are automatically separated, and errors are verified in order of the document and logic to improve document accuracy accordingly. Through document debugging technology, errors in the document are identified in real time. Furthermore, it is necessary to predict the changes that intelligent document processing will bring to document management work, in particular, the impact on documents and utilization tasks that are double managed due to various formulas and prepare necessary capabilities in the future.