• Journal of KIISE
• /
• v.45 no.2
• /
• pp.157-164
• /
• 2018

Due to the revolutionary advances in deep learning, performance of pattern recognition has increased significantly in many applications like speech recognition and image recognition, and some systems outperform human-level intelligence in specific domains. Unlike pattern recognition, in this paper, we focus on generating Korean sentences based on a few Korean sentences. We apply variational recurrent auto-encoder (VRAE) and modify the model considering some characteristics of Korean sentences. To reduce the number of words in the model, we apply a word spacing model. Also, there are many Korean sentences which have the same meaning but different word order, even without subjects or objects; therefore we change the unidirectional encoder of VRAE into a bidirectional encoder. In addition, we apply an interpolation method on the encoded vectors from the given sentences, so that we can generate new sentences which are similar to the given sentences. In experiments, we confirm that our proposed method generates better sentences which are semantically more similar to the given sentences.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.103-110
• /
• 2023

With the spread of the Internet, anonymous communities emerged along with the activation of communities for communication between people, and many users are doing harm to others, such as posting aggressive posts and leaving comments using anonymity. In the past, administrators directly checked posts and comments, then deleted and blocked them, but as the number of community users increased, they reached a level that managers could not continue to monitor. Initially, word filtering techniques were used to prevent malicious writing from being posted in a form that could not post or comment if a specific word was included, but they avoided filtering in a bypassed form, such as using similar words. As a way to solve this problem, deep learning was used to monitor posts posted by users in real-time, but recently, the community uses words that can only be understood by the community or from a human perspective, not from a general Korean word. There are various types and forms of characters, making it difficult to learn everything in the artificial intelligence model. Therefore, in this paper, we proposes a preprocessing technique in which each character of a sentence is imaged using a CNN model that learns the consonants, vowel and spacing images of Korean word and converts characters that can only be understood from a human perspective into characters predicted by the CNN model. As a result of the experiment, it was confirmed that the performance of the LSTM, BiLSTM and CNN-BiLSTM models increased by 3.2%, 3.3%, and 4.88%, respectively, through the proposed preprocessing technique.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.87-94
• /
• 2020

Social reviews such as SNS feeds and blog articles have been widely used to extract keywords reflecting opinions and complaints from users' perspective, and often include proper nouns or new words reflecting recent trends. In general, these words are not included in a dictionary, so conventional morphological analyzers may not detect and extract those words from the reviews properly. In addition, due to their high processing time, it is inadequate to provide analysis results in a timely manner. This paper presents a method for efficient keyword extraction from social reviews based on the notion of cohesion scoring. Cohesion scores can be calculated based on word frequencies, so keyword extraction can be performed without a dictionary when using it. On the other hand, their accuracy can be degraded when input data with poor spacing is given. Regarding this, an algorithm is presented which improves the existing cohesion scoring mechanism using the structure of a word tree. Our experiment results show that it took only 0.008 seconds to extract keywords from 1,000 reviews in the proposed method while resulting in 15.5% error ratio which is better than the existing morphological analyzers.

• Communications of Mathematical Education
• /
• v.27 no.4
• /
• pp.391-406
• /
• 2013

Most of mathematical terms in Korean are Sino-Korean words. It is necessary to find the efficient ways to teach Sino-Korean mathematical terms to mathematics teachers and students who dot not know Chinese characters well and use only Korean alphabet in mathematics. Especially, we have to avoid the inappropriate Sino-Korean words which can cause misconceptions and can distinguish homophones by Korean alphabet. We may use native Korean terms to do that and the national curriculum can play an important role. In this paper, we investigate the way of improving mathematics terms in Korea with concrete examples.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.3
• /
• pp.74-80
• /
• 2002

There are many researches on post-processing methods for the Korean continuous speech recognition enhancement using natural language processing techniques. It is very difficult to use a formal morphological analyzer for improving the speech recognition because the analysis technique of natural language processing is mainly for formal written languages. In this paper, we propose a speech recognition enhancement model using syntactic unit of morphemes. This approach uses the functional word level longest match which dose not consider spacing words. We describe the post-processing mechanism for the improving speech recognition by using proposed model which uses the relationship of phonological structure information between predicates md auxiliary predicates or bound nouns that are frequently occurred in Korean sentences.

• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.5-11
• /
• 2008

한국어 띄어쓰기에서 통계적 모델을 사용한 기존의 연구들은 최대우도추정(Maximum Likelihood Estimation)에 기반하고 있다. 그러나 최대우도추정은 자료부족 시 부정확한 결과를 주는 단점이 있다. 본 연구는 이에 대한 대안으로 사용자 입력을 고려하는 베이지언 파라미터 추정(Bayesian parameter estimation)을 제안한다. 기존 연구가 사용자 입력을 교정 대상으로만 간주한 것에 비해, 제안 방법은 사용자 입력을 교정 대상이면서 동시에 학습의 대상으로 해석한다. 제안하는 방법에서 사용자 입력은 학습 말뭉치의 자료부족에서 유발되는 부정확한 파라미터 추정(parameter estimation)을 방지하는 역할을 수행하고, 학습 말뭉치는 사용자 입력의 불확실성을 보완하는 역할을 수행한다. 실험을 통해 문어체 말뭉치, 통신환경 구어체 말뭉치, 웹 게시판 등 다양한 종류의 말뭉치와 다양한 통계적 모델에 대해 제안 방법이 효과적임을 알 수 있다.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.7
• /
• pp.27-35
• /
• 1999

Researches on the recognition of handwritten script have been conducted under the assumption that the isolated recognition units are provided as inputs. However, in practical recognition system designs, providing the isolated recognition unit is an challenge due to various writing syles. This paper proposes an approach for segmenting words from lines of unconstrained handwritten text, without help of recognition. In contrast to the conventional approaches which are based on physical gaps between connected components, clues that reflect the author's writing style, in terms of spacing, are extracted and utilized for the segmentation using a simple neural network. The clues are from character segments and include normalized heights and intervals of the segments. Effectiveness of the proposed approach compared with the conventional connected component based approaches in terms of word segmentation performance was evaluated by experiments.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.65-74
• /
• 2021

Recently, studies on Korean spelling correction have been actively conducted based on machine translation and automatic noise generation. These methods generate noise and use as train and data set. This has limitation in that it is difficult to accurately measure performance because it is unlikely that noise other than the noise used for learning is included in the test set In addition, there is no practical error type standard, so the type of error used in each study is different, making qualitative analysis difficult. This paper proposes new 'error type classification' for deep learning-based Korean spelling correction research, and error analysis perform on existing commercialized Korean spelling correctors (System A, B, C). As a result of analysis, it was found the three correction systems did not perform well in correcting other error types presented in this paper other than spacing, and hardly recognized errors in word order or tense.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.7
• /
• pp.2595-2602
• /
• 2010

This paper introduces a mobile spam filtering system that considers the style of short text messages sent to mobile phones for detecting spam. The proposed system not only relies on the occurrence of content words as previously suggested but additionally leverages the style information to reduce critical cases in which legitimate messages containing spam words are mis-classified as spam. Moreover, the accuracy of spam classification is improved by normalizing the messages through the correction of word spacing and spelling errors. Experiment results using real world Korean text messages show that the proposed system is effective for Korean mobile spam filtering.

• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.427-434
• /
• 2009

With the rapid evolution of the Internet and mobile environments, text including spelling errors such as newly-coined words and abbreviated words are widely used. These spelling errors make it difficult to develop NLP (natural language processing) applications because they decrease the readability of texts. To resolve this problem, we propose a spelling error correction model using a spelling error correction dictionary and a newspaper corpus. The proposed model has the advantage that the cost of data construction are not high because it uses a newspaper corpus, which we can easily obtain, as a training corpus. In addition, the proposed model has an advantage that additional external modules such as a morphological analyzer and a word-spacing error correction system are not required because it uses a simple string matching method based on a correction dictionary. In the experiments with a newspaper corpus and a short message corpus collected from real mobile phones, the proposed model has been shown good performances (a miss-correction rate of 7.3%, a F1-measure of 97.3%, and a false positive rate of 1.1%) in the various evaluation measures.