• The KIPS Transactions:PartB
• /
• v.19B no.2
• /
• pp.135-148
• /
• 2012

This paper proposes a model for recognizing sentential paraphrases through Predicate-Argument Tuple (PAT)-based approximate alignment between two texts. We cast the paraphrase recognition problem as a binary classification by defining and applying various alignment features which could effectively express the semantic relatedness between two sentences. Experiment confirmed the potential of our approach and error analysis revealed various paraphrase patterns not being solved by our system, which can help us devise methods for further performance improvement.

• International Journal of Contents
• /
• v.6 no.2
• /
• pp.1-5
• /
• 2010

The rapid growth in communication technology has led to the development of effective ways of sharing ideas and information in the form of speech and images. Understanding this information has become an important research issue and drawn the attention of many researchers. Text in a digital image contains much important information regarding the scene. Detecting and extracting this text is a difficult task and has many challenging issues. The main challenges in extracting text from natural scene images are the variation in the font size, alignment of text, font colors, illumination changes, and reflections in the images. In this paper, we propose a connected component based method to automatically detect the text region in natural images. Since text regions in mages contain mostly repetitions of vertical strokes, we try to find a pattern of closely packed vertical edges. Once the group of edges is found, the neighboring vertical edges are connected to each other. Connected regions whose geometric features lie outside of the valid specifications are considered as outliers and eliminated. The proposed method is more effective than the existing methods for slanted or curved characters. The experimental results are given for the validation of our approach.

• Proceeding of EDISON Challenge
• /
• 2015.03a
• /
• pp.177-183
• /
• 2015

$\text\tiny{D}$-Psicose 3-Epimerase (DPE)는 $\text\tiny{D}$-Fructose의 C3 Epimerase로써 $\text\tiny{D}$-Fructose를 $\text\tiny{D}$-Psicose로 전환해 주는 효소이다. $\text\tiny{D}$-Psicose는 설탕 대신 사용하는 감미료로 몸에 흡수되지 않아 칼로리가 없다고 알려져 있고 자연에서는 오로지 DPE에 의해서만 생산되는 희귀당이다. 이에 따라 DPE를 통한 $\text\tiny{D}$-Psicose 대량생산의 필요성이 대두되고 있는 등 이 분야에 대한 관심이 뜨거운 실정이다. 본 연구팀은 이 당과 관련된 작용기작 연구를 수행하기 위하여 아직 단백질 3차구조가 알려지지 않은 Clostridium hylemonae DPE (chDPE) 단백질의 3차 구조예측 연구를 수행 하였다. 우리는 HHsearch를 이용하여 agrobacterium tumefaciens의 DPE 외 2개의 구조를 호몰로지 모델링 연구를 위한 주형으로 선정하였다. 다음으로 PROMALS3D를 이용하여 주형들과 chDPE의 multiple sequence alignment를 수행하였고 이를 바탕으로 3차구조 예측 연구를 수행 하였다. 예측된 구조를 검증하기 위하여 ProSA와 Ramachandran plot분석을 이용하였고 Ramachandran plot에서 단백질의 94.8%에 해당하는 잔기들이 favoured regions에 위치하였다. ProSA에서는 Z-score값이 -9.3으로 X-선 결정학이나 핵자기 공명법으로 밝혀진 구조들에서 관측되는 범위 내에 위치하였다. 나아가 예측된 구조에 $\text\tiny{D}$-Psicose와 $\text\tiny{D}$-Fructose의 결합모드를 규명하기 위하여 도킹을 시도하였다. 이번 연구를 통하여 chDPE의 구조를 예측 할 수 있었고 이를 바탕으로 이 단백질의 기능을 이해하는데 도움을 줄 것으로 기대된다.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.761-772
• /
• 2020

This paper presents an automatic proficiency assessment method for a non-native Korean read utterance using bidirectional long short-term memory (BLSTM)-based acoustic models (AMs) and speech data augmentation techniques. Specifically, the proposed method considers two scenarios, with and without prompted text. The proposed method with the prompted text performs (a) a speech feature extraction step, (b) a forced-alignment step using a native AM and non-native AM, and (c) a linear regression-based proficiency scoring step for the five proficiency scores. Meanwhile, the proposed method without the prompted text additionally performs Korean speech recognition and a subword un-segmentation for the missing text. The experimental results indicate that the proposed method with prompted text improves the performance for all scores when compared to a method employing conventional AMs. In addition, the proposed method without the prompted text has a fluency score performance comparable to that of the method with prompted text.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.2
• /
• pp.231-235
• /
• 2008

Recently we witnessed a few scandals on plagiarism among academic paper and novels. Plagiarism on documents is getting worse more frequently. Although plagiarism on English had been studied so long time, we hardly find the systematic and complete studies on plagiarisms in Korean documents. Since the linguistic features of Korean are quite different from those of English, we cannot apply the English-based method to Korean documents directly. In this paper, we propose a new plagiarism detecting method for Korean, and we throughly tested our algorithm with one benchmark Korean text corpus. The proposed method is based on "k-mer" and "local alignment" which locates the region of plagiarized document pairs fast and accurately. Using a Korean corpus which contains more than 10 million words, we establish a probability model (or local alignment score (random similarity by chance). The experiment has shown that our system was quite successful to detect the plagiarized documents.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.228-231
• /
• 2011

최근 표절에 대한 사회적 관심이 꾸준히 높아지고 있는 가운데, 기계적으로 유사한 문서를 탐색하는 방법에 대한 많은 연구가 이루어지고 있다. 이 중 생물정보학에서 유전자 서열을 분석하기 위해 사용되는 '지역 정렬(local alignment)' 기법은 문서 간 유사 영역을 탐색하는 데에 유용하다. 한편 한글에는 조사가 존재하는데, 이 때문에 한글 문장은 각 품사의 순서에 큰 영향을 받지 않는다. 이러한 한글의 특성을 이용해 기존 문서의 어순만 바꾼 문장을 생성할 경우, 지역 정렬을 이용한 탐색 방법으로는 이를 찾아내기 힘들다. 본 논문에서는 한글의 특성을 고려하여 어순과 관계없이 해당 영역의 유사성을 찾아내는 새로운 한글 유사 문서 탐색 방법을 제시한다. 이를 위하여, 성분 정렬(composition alignment) 기법을 적용한다. 성분 정렬 기법은 생물학에서 생물의 진화 과정이나 돌연변이 DNA 등 서열의 순서가 일부 뒤바뀌는 것을 허용하면서 유사한 시퀀스를 찾는 기법으로 기존의 방법보다 더욱 유연하고 민감한 방법이라 할 수 있다. 이를 적용하여 한글 문서를 탐색한 결과, 일반적인 문장 및 거의 동일한 문장 간의 유사도 점수는 큰 변화가 없었으나, 어순을 바꾼 문장의 경우 기존의 방법보다 평균 35.34% 가량 민감하게 탐색할 수 있었다. 추후 한글에 대한 초성 추출 및 성분 정렬 방법을 응용하여 다단계 구조의 유사 문서 탐색 방법에 대해 연구할 계획이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.414-417
• /
• 2011

단어 필터링 기법의 개발에 있어서 가장 큰 난제는 정상단어를 금지어로 인식하여 이를 차단하는 오탐지 문제이다. 이를 방지하기 위하여 다양한 문장에 대한 면밀하고 광범위한 검사가 필수적이나 일반적으로 쉽게 접근할 수 있는 데이터는 주로 단어 위주로 구성된 검증 데이터로 문장 또는 구절로 구성된 데이터의 양은 실제 검증에 활용하기에는 충분하지 못하다. 본 논문에서는 웹에서 수집한 방대한 양의 말뭉치 데이터에 반전역정열(Semi-Global Alignment)을 적용하여 주어진 금지어가 사용되거나 금지어와 유사한 단어가 존재하는 구간을 탐색함으로써 단어 필터링 시스템에서 범용적으로 사용될 수 있는 문장형 평가 데이터를 수집하는 시스템을 제안하고 해당 기법을 통하여 수집한 문장 단위 데이터를 분석하고 단어 필터링 시스템이 오탐지 방지를 위해 가져야할 요소들에 대하여 검토해 본다.

• Journal of KIISE
• /
• v.41 no.9
• /
• pp.728-743
• /
• 2014

Finger printing and sequence alignment are well-known approaches for document similarity comparison. A fingerprinting method is simple and fast, but it can not find particular similar regions. A string alignment method is used for identifying regions of similarity by arranging the sequences of a string. It has an advantage of finding particular similar regions, but it also has a disadvantage of taking more computing time. The Multi-Level Alignment (MLA) is a new method designed for taking the advantages of both methods. The MLA divides input documents into uniform length blocks, and then extracts fingerprints from each block and calculates similarity of block pairs by comparing the fingerprints. A similarity table is created in this process. Finally, sequence alignment is used for specifying longest similar regions in the similarity table. The MLA allows users to change block's size to control proportion of the fingerprint algorithm and the sequence alignment. As a document is divided into several blocks, similar regions are also fragmented into two or more blocks. To solve this fragmentation problem, we proposed a united block method. Experimentally, we show that computing document's similarity with the united block is more accurate than the original MLA method, with minor time loss.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.113-120
• /
• 2009

Currently the verbal abuse in text message over on-line game is so serious. However we do not have any effective policy or technical tools yet. Till now in order to cope with this problem, the online game service providers have accumulated a set of forbidden words and applied this list on the textual word used in on-line game, which is called 'Swear filter'. But young on-line game players easily avoid this filtering method by coining another words which is not kept in the list. Especially Korean is very easy to make new variations of a vulgar word. In this paper, we propose one smart filtering algorithm to identify newly coined profanities. Important features of our method include the canonical form transformation of coined profanities, semi-global alignment between in the level of consonant and vowel units. For experiment, we have collected more than 1000 newly coined vulgar words in on-line gaming sites and tested these word against our methods. where our system have successfully filtered more than 90% of those newly coined vulgar words.

• Journal of Information Technology Applications and Management
• /
• v.20 no.3
• /
• pp.19-30
• /
• 2013

The objective of this research is to identify a web portal's specific functions and layouts that are aligned with personality trait of an individual internet user. This first stage of the overall research project intends to check whether the research instrument, namely the NEO Five Factors Inventory (NEO-FFI), is applicable to assess the personality traits of Thai internet users. Based on these personality traits, text-based description of functions/layouts of a web portal was developed and given to professional designers to mock up example web portal pages. These web portal pages were in alignment with individual personality traits. Rating data on the functions/layouts corresponding to individual personality traits were collected from an online survey of 207 Thai internet users. Results showed that respondents gave more consistent rating to the functions/layouts close to their individual personality traits identified in the text-based descriptions than in the mocked-up web portal pages.