• 대한음성학회지:말소리
• /
• 제46호
• /
• pp.117-126
• /
• 2003

This paper presents our language model adaptation for Korean spontaneous speech recognition. Korean spontaneous speech is observed various characteristics of content and style such as filled pauses, word omission, and contraction as compared with the written text corpus. Our approaches focus on improving the estimation of domain-dependent n-gram models by relevance weighting out-of-domain text data, where style is represented by n-gram based tf/sup */idf similarity. In addition to relevance weighting, we use disfluencies as Predictor to the neighboring words. The best result reduces 9.7% word error rate relatively and shows that n-gram based relevance weighting reflects style difference greatly and disfluencies are good predictor also.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2018년도 제58차 하계학술대회논문집 26권2호
• /
• pp.441-442
• /
• 2018

본 논문에서는 입시상담을 위한 챗봇 시스템을 텍스트 유사도 기반으로 개발하였다. 텍스트를 인지하여 답변을 제공해 주는 방식이며 실시간을 요하는 데이터들은 크롤링한 데이터를 가공을 한 후 사용자에게 대답을 해주고 사용자가 답변에 얼마나 좋은 정보인지 체크하여 그에 맞는 답변을 내어 준다. 사용자의 텍스트를 인식하는 것은 텍스트 유사도를 이용하여 정확하게 인지하고 사용자의 질문과 답변을 서버 DB에 저장을 하여 비슷한 질문이 있을 경우 저장된 답변과 평점을 이용하여 답변을 제공한다.

• 한국IT서비스학회지
• /
• 제18권4호
• /
• pp.135-149
• /
• 2019

Recently, there are many researches for extracting meaningful information from large amount of text data. Among various applications to extract information from text, topic modeling which express latent topics as a group of keywords is mainly used. Topic modeling presents several topic keywords by term/topic weight and the quality of those keywords are usually evaluated through coherence which implies the similarity of those keywords. However, the topic quality evaluation method based only on the similarity of keywords has its limitations because it is difficult to describe the content of a topic accurately enough with just a set of similar words. In this research, therefore, we propose topic keywords reorganizing method to improve the identifiability of topics. To reorganize topic keywords, each document first needs to be labeled with one representative topic which can be extracted from traditional topic modeling. After that, classification rules for classifying each document into a corresponding label are generated, and new topic keywords are extracted based on the classification rules. To evaluated the performance our method, we performed an experiment on 1,000 news articles. From the experiment, we confirmed that the keywords extracted from our proposed method have better identifiability than traditional topic keywords.

• 정보처리학회논문지B
• /
• 제12B권2호
• /
• pp.115-122
• /
• 2005

영상이 다른 영상을 포함하고 있는 경우, 이득 영상의 인치 여부를 판단하는 부분 영상 매칭 방법은 대부분 자연 영상을 대상으로 연구되고 있다. 본 논문에서는 자연 영상이 아닌 텍스트 영상을 매칭하는데 효과적인 두 가지 기법, 즉 메쉬 기반 방법과 상관성 기반 방법을 제안하고자 하다. 메쉬 기반 방법은 두 영상의 일치하는 모서리론 찾은 후 겹치는 영역에 대한 메쉬 특징을 이용하여 유사 여부를 판단하는 것으로, 일치 영역 검색 단계와 유사성 측정 단계로 구성된다. 상관성 기반 방법은 FFT를 이용하여 두 영상의 상관성을 계산함으로써 유사도를 측정한다. 우편 자동화 시스템에서 텍스트 영상을 검증하는 분야에 세안 방법을 적용한 견과, 메쉬 기반 방법은 $90.1\%$, 상관성 기반 방법은 $92.7\%$의 성능을 나타내었다.

• 한국동물학회:학술대회논문집
• /
• 한국동물학회 2001년도 공동 춘계학술대회
• /
• pp.49-49
• /
• 2001

No Abstract, See Full Text

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.251-252
• /
• 2007

The thesis proposed the Text Extraction Algorithm which is a text extraction algorithm which uses the Coiflet Wavelet, YCbCr Color model and the close curve edge feature of adaptive LoG Operator in order to complement the demerit of the existing research which is weak in complexity of background, variety of light and disordered line and similarity of text and background color. This thesis is simulated with natural images which include naturally text area regardless of size, resolution and slant and so on of image. And the proposed algorithm is confirmed to an excellent by compared with an existing extraction algorithm in same image.

• 한국컴퓨터정보학회논문지
• /
• 제24권7호
• /
• pp.31-37
• /
• 2019

Citation-based article summarization is to create a shortened text for an academic article, reflecting the content of citing sentences which contain other's thoughts about the target article to be summarized. To deal with the problem, this study introduces an extractive summarization method based on calculating a linear combination of various sentence salience scores, which represent the degrees to which a candidate sentence reflects the content of author's abstract text, reader's citing text, and the target article to be summarized. In the current study, salience scores are obtained by computing surface-level textual similarities. Experiments using CL-SciSumm datasets show that the proposed method parallels or outperforms the previous approaches in ROUGE evaluations against SciSumm-2017 human summaries and SciSumm-2016/2017 community summaries.

• The Journal of the Acoustical Society of Korea
• /
• 제23권2E호
• /
• pp.51-55
• /
• 2004

In this paper, we propose a style-specific language model adaptation scheme using n-gram based tf*idf similarity for Korean spontaneous speech recognition. Korean spontaneous speech shows especially different style-specific characteristics such as filled pauses, word omission, and contraction, which are related to function words and depend on preceding or following words. To reflect these style-specific characteristics and overcome insufficient data for training language model, we estimate in-domain dependent n-gram model by relevance weighting of out-of-domain text data according to their n-. gram based tf*idf similarity, in which in-domain language model include disfluency model. Recognition results show that n-gram based tf*idf similarity weighting effectively reflects style difference.

• Journal of Mechanical Science and Technology
• /
• 제15권9호
• /
• pp.1339-1345
• /
• 2001

Laminar film condensation of a saturated pure vapor in forced flow over a flat plate is analyzed as boundary layer solutions. Similarity solutions for some real fluids are presented as a function of modified Jakob number (C$\_$pι/ ΔΤ/Prh$\_$fg/) with property ratio (No Abstract.see full/text) and Pγ as parameters and compared with approximate solutions which were obtained from energy and momentum equations without convection and inertia terms in liquid flow. Approximate solutions agree well with the similarity solutions when the values of modified Jakob number are less then 0.1 near 1 atmospheric pressure.

• International Journal of Advanced Culture Technology
• /
• 제8권2호
• /
• pp.289-296
• /
• 2020

Software copyright are written in text form of documents and stored as files, so it is easy to expose on an illegal copyright. The IOT framework configuration and service environment are also evaluated in software structure and revealed to replication environments. Illegal copyright can be easily created by intelligently modifying the program code in the framework system. This paper deals with similarity comparison to determine the suspicion of illegal copying. In general, original source code should be provided for similarity comparison on both. However, recently, the suspected developer have refused to provide the source code, and comparative evaluation are performed only with executable code. This study dealt with how to analyze the similarity with the execution code and the circuit configuration and interface state of the system without the original source code. In this paper, we propose a method of analyzing the data of the object without source code and verifying the similarity comparison result through evaluation examples.