• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1255-1258
• /
• 1998

Hidden Markov Model (HMM) is the most widely used method in speech recognition. In general, HMM parameters are trained to have maximum likelihood (ML) for training data. This method doesn't take account of discrimination to other words. To complement this problem, this paper proposes a word verification method by re-recognition of the recognized word and its similar word using the discriminative function between two words. The similar word is selected by calculating the probability of other words to each HMM. The recognizer haveing discrimination to each word is realized using the weighting to each state and the weighting is calculated by genetic algorithm.

• Journal of Computing Science and Engineering
• /
• 제10권4호
• /
• pp.103-110
• /
• 2016

Emotion recognition is an important component of affective computing, and is significant in the implementation of natural and friendly human-computer interaction. An effective approach to recognizing emotion from text is based on a machine learning technique, which deals with emotion recognition as a classification problem. However, in emotion recognition, the texts involved are usually very short, leaving a very large, sparse feature space, which decreases the performance of emotion classification. This paper proposes to resolve the problem of feature sparseness, and largely improve the emotion recognition performance from short texts by doing the following: representing short texts with word cluster features, offering a novel word clustering algorithm, and using a new feature weighting scheme. Emotion classification experiments were performed with different features and weighting schemes on a publicly available dataset. The experimental results suggest that the word cluster features and the proposed weighting scheme can partly resolve problems with feature sparseness and emotion recognition performance.

• 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.

• 정보관리연구
• /
• 제42권2호
• /
• pp.193-210
• /
• 2011

이 연구는 단어 중의성 해소를 위해 SVM 분류기가 최적의 성능을 가져오는 문맥창의 크기와 다양한 가중치 방법을 파악하고자 하였다. 실험집단으로 한글 신문기사를 적용하였다. 문맥창의 크기로 지역 문맥은 좌우 3단어, 한 문장, 그리고 좌우 50바이트 크기를 사용하였으며, 전역문맥으로 신문기사 전체를 대상으로 하였다. 가중치 부여 기법으로는 단순빈도인 이진 단어빈도와 단순 단어빈도를, 정규화 빈도로 단순 또는 로그를 취한 단어빈도 ${\times}$ 역문헌빈도를 사용하였다. 실험 결과 문맥창의 크기는 좌우 50 바이트가 가장 좋은 성능을 보였으며, 가중치 부여 방법은 이진 단어빈도가 가장 좋은 성능을 보였다.

• 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.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.83-86
• /
• 2003

This paper presents our style-based language model adaptation for Korean conversational speech recognition. Korean conversational speech is observed various characteristics of content and style such as filled pauses, word omission, and contraction as compared with the written text corpora. For style-based language model adaptation, we report two approaches. 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*idf similarity. In addition to relevance weighting, we use disfluencies as predictor to the neighboring words. The best result reduces 6.5％ word error rate absolutely and shows that n-gram based relevance weighting reflects style difference greatly and disfluencies are good predictor.

• 정보관리학회지
• /
• 제1권1호
• /
• pp.43-62
• /
• 1984

본(本) 연구는 두 개의 중요한 목적(目的)들을 가지고 있다. 첫째 목적(目的)은 새로운 단어(單語) 가중기법(加重技法)을 고안하는 것이다. 두번째 목적(目的)은 제안된 단어(單語) 가중기법(加重技法)과 다른 네개의 단어(單語) 가중기법(加重技法)들의 문헌검색결과들을 평가하는 것이다. 본 연구에서 실행된 실험결과는 비교적 간단한 스파크 죤스(Sparck Jones)의 역문헌빈도 가중기법(加重技法)과 제안된 단어(單語) 가중기법(加重技法)의 검색결과들이 더 복잡한 계산을 요하는 다른 세개의 단어(單語) 가중기법(加重技法)들의 검색결과들보다 더 나았다.

• 정보관리학회지
• /
• 제4권1호
• /
• pp.47-86
• /
• 1987

본 연구는 한글자동색인에 관한 연구로 한국전자통신연구소의 DOCUMENT Data Base로부터 299개 문헌의 제목과 초록을 무작위로 추출하여 단어분리를 시도하고, 분리된 단어군, 인식어를 제외한 단어군, 인식어와 불용어를 제외한 단어군, 그리고 인식어와 불용어를 제외하고 복합어를 구성하여 포함한 단어군 등 4개의 시험군을 설정한 후, 파오의 전환점 산출기과 스파크죤스의 역문헌 가중기법, 살톤의 문헌분리 가중기법을 적용하여 색인어를 선정하고 이를 비교 평가하여 한글문헌의 자동색인 방안을 모색하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 전기.전자공학 학술대회 논문집
• /
• pp.179-182
• /
• 1988

Since the bits in any encoded PCM word are of different importance to the bit positions, in order to improve the signal to noise ratio the technique that the encoded signal bits are weighted for the QPSK transmission system, is presented. Also the erasure zone is established at the detector, such that if the output falls into the erasure zone, the regenerated sample is replaced by interpolation. Two weighting methods are shown here. One is the method that the same weighting profile is used to Q and I dimension in QPSK signal constellations. The other is diferent weighting to Q and I dimension. The gains of this new technique in overall signal s/n compared to conventional QPSK transmission system were 5 db and 2db, respectively.

• 한국정보통신학회논문지
• /
• 제17권2호
• /
• pp.347-354
• /
• 2013

본 논문은 확장된 용어를 기반으로 용어의 가중치를 재산정하여 문서군집의 성능을 향상시키는 방법을 제안한다. 제안된 방법은 의미특징을 이용하여 군집문서의 중요 용어를 추출하고, 워드넷을 이용하여 용어를 확장함으로서 문서의 주제를 잘 나타낼 수 있다. 또한 확장된 용어를 기반으로 하여 용어의 가중치를 재산정함으로써 문서군집의 성능을 높일 수 있다. 실험결과 제안방법을 적용한 문서군집방법이 적용하지 않은 문서군집 방법에 비해서 좋은 성능을 보인다.