• Speech Sciences
• /
• v.5 no.1
• /
• pp.49-62
• /
• 1999

This study is concerned with the educational program Visual Analysis Tool (VAT) for sound development for foreign intonation using personal computer. The VAT can run on IBM-PC 386 compatible or higher. It shows the spectrogram, waveform, intensity and the pitch contour. The system can work freely on either waveform zoom in-out or the documentation of measured value. In this paper, intensity and pitch contour information were used. Twelve French sentences were recorded from a French conversational tape. And three Korean participated in this study. They spoke out twelve sentences repeatly and trid to make the same pitch contour - by visually matching their pitcgh contour to the native speaker's. A sentences were recorded again when the participants themselves became familiar with intonation, intensity and pauses. The difference of pitch contour(rising or falling), pitch value, energy, total duration of sentences and the boundary of rhythmic group between native speaker's and theirs before and after training were compared. The results were as following: 1) In a declarative sentence: a native speaker's general pitch contour falls at the end of sentences. But the participant's pitch contours were flat before training. 2) In an interrogative: the native speaker made his pitch contours it rise at the end of sentences with the exception of wh-questions (qu'est-ce que) and a pitch value varied a greath. In the interrogative 'S + V' form sentences, we found the pitch contour rose higher in comparison to other sentences and it varied a great deal. 3) In an exclamatory sentence: the pitch contour looked like a shape of a mountain. But the participants could not make it fall before or after training.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.521-528
• /
• 2021

Existing image analysis systems in use in the military field are carried out by readers analyzing and identifying images themselves, writing and disseminating related content, and in this process, repetitive tasks are frequent, resulting in workload. In this paper, to solve the previous problem, we proposed an algorithm that can operate the Seq2Seq model on a word basis, which operates on a sentence basis, and applied the Attention technique to improve accuracy. In addition, by applying the Beam Search technique, we would like to recommend various current identification sentences based on the past identification contents of a specific area. It was confirmed through experiments that the Beam Search technique recommends sentences more effectively than the existing greedy Search technique, and confirmed that the accuracy of recommendation increases when the size of Beam is large.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.367-374
• /
• 2022

In this paper, correlation analysis between speech characteristics and the dose of antipsychotic drugs was performed. To investigate the pattern of speech characteristics of ExtraPyramidal Symptoms (EPS) related to voice change, a common side effect of antipsychotic drugs, a Korean-based extrapyramidal symptom speech corpus was constructed through the sentence development. Through this, speech patterns of EPS and non-EPS groups were investigated, and in particular, a strong speech feature correlation was shown in the EPS group. In addition, it was confirmed that the type of speech sentence affects the speech feature pattern, and these results suggest the possibility of early detection of antipsychotics-induced EPS based on the speech features.

• The Research Journal of the Costume Culture
• /
• v.2 no.2
• /
• pp.317-335
• /
• 1994

The purpose of this thesis is to analyze the relation of the mentalistics linguistics and costume, and to clarify the relationship between language as psychological expressions and costume to understand the phenomena of human costume behavior more deeply and comprehensively. As for the analysis of he costume phenomena, Noam Chomsky's psychological linguistic theory were applied to costume system. In this respect, particularly, by means of Chomsky's later theory(1965), the costume behavior were analyzed. The followings are the findings of the analysis : 1. The Syntactic Component: (※ See Full-Text) 2. The Semantic Component. The costme behavior is similar to a language system. Just as one morpheme or a phrase and phrases make different sentences, so various methods wearing costume make different sentences, so various methods wearing costume make different forms is costume. Language and costume have dictionary entry showing the meaning of vocabulary, and rules combining the individual meaning of the dictionary entry to complete the sentence.

• Journal of Information Technology Applications and Management
• /
• v.16 no.1
• /
• pp.21-36
• /
• 2009

As the World Wide Web (WWW) has become a major channel for information delivery, the data accumulated in the Internet increases at an incredible speed, and it derives the advances of information search technologies. It is the search engine that solves the problem of information overloading and helps people to identify relevant information. However, as search engines become a powerful tool for finding information, the opportunities of plagiarizing have increased significantly in e-Learning. In this paper, we developed an online plagiarism detection system for detecting plagiarized documents that incorporates the functions of search engines and acts in exactly the same way of plagiarizing. The plagiarism detection system uses morpheme analysis to improve the performance and sentence-based comparison to investigate document comes from multiple sources. As a result of applying this system in e-Learning, the performance of plagiarism detection was improved.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1321-1325
• /
• 1993

This paper investigates the use of Fuzzy vector quantizer(FVQ) in speech synthesis. To compress speech data, we employ K-means algorithm to design codebook and then FVQ technique is used to analysize input speech vectors based on the codebook in an analysis part. In FVQ synthesis part, analysis data vectors generated in FVQ analysis is used to synthesize the speech. We have fined that synthesized speech quality depends on Fuzziness values in FVQ, and the optimum fuzziness values maximized synthesized speech SQNR are related with variance values of input speech vectors. This approach is tested on a sentence, and we compare synthesized speech by a convensional VQ with synthesized speech by a FVQ with optimum Fuzziness values.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.59-83
• /
• 2018

With the increasing importance of sentiment analysis to grasp the needs of customers and the public, various types of deep learning models have been actively applied to English texts. In the sentiment analysis of English texts by deep learning, natural language sentences included in training and test datasets are usually converted into sequences of word vectors before being entered into the deep learning models. In this case, word vectors generally refer to vector representations of words obtained through splitting a sentence by space characters. There are several ways to derive word vectors, one of which is Word2Vec used for producing the 300 dimensional Google word vectors from about 100 billion words of Google News data. They have been widely used in the studies of sentiment analysis of reviews from various fields such as restaurants, movies, laptops, cameras, etc. Unlike English, morpheme plays an essential role in sentiment analysis and sentence structure analysis in Korean, which is a typical agglutinative language with developed postpositions and endings. A morpheme can be defined as the smallest meaningful unit of a language, and a word consists of one or more morphemes. For example, for a word '예쁘고', the morphemes are '예쁘(= adjective)' and '고(=connective ending)'. Reflecting the significance of Korean morphemes, it seems reasonable to adopt the morphemes as a basic unit in Korean sentiment analysis. Therefore, in this study, we use 'morpheme vector' as an input to a deep learning model rather than 'word vector' which is mainly used in English text. The morpheme vector refers to a vector representation for the morpheme and can be derived by applying an existent word vector derivation mechanism to the sentences divided into constituent morphemes. By the way, here come some questions as follows. What is the desirable range of POS(Part-Of-Speech) tags when deriving morpheme vectors for improving the classification accuracy of a deep learning model? Is it proper to apply a typical word vector model which primarily relies on the form of words to Korean with a high homonym ratio? Will the text preprocessing such as correcting spelling or spacing errors affect the classification accuracy, especially when drawing morpheme vectors from Korean product reviews with a lot of grammatical mistakes and variations? We seek to find empirical answers to these fundamental issues, which may be encountered first when applying various deep learning models to Korean texts. As a starting point, we summarized these issues as three central research questions as follows. First, which is better effective, to use morpheme vectors from grammatically correct texts of other domain than the analysis target, or to use morpheme vectors from considerably ungrammatical texts of the same domain, as the initial input of a deep learning model? Second, what is an appropriate morpheme vector derivation method for Korean regarding the range of POS tags, homonym, text preprocessing, minimum frequency? Third, can we get a satisfactory level of classification accuracy when applying deep learning to Korean sentiment analysis? As an approach to these research questions, we generate various types of morpheme vectors reflecting the research questions and then compare the classification accuracy through a non-static CNN(Convolutional Neural Network) model taking in the morpheme vectors. As for training and test datasets, Naver Shopping's 17,260 cosmetics product reviews are used. To derive morpheme vectors, we use data from the same domain as the target one and data from other domain; Naver shopping's about 2 million cosmetics product reviews and 520,000 Naver News data arguably corresponding to Google's News data. The six primary sets of morpheme vectors constructed in this study differ in terms of the following three criteria. First, they come from two types of data source; Naver news of high grammatical correctness and Naver shopping's cosmetics product reviews of low grammatical correctness. Second, they are distinguished in the degree of data preprocessing, namely, only splitting sentences or up to additional spelling and spacing corrections after sentence separation. Third, they vary concerning the form of input fed into a word vector model; whether the morphemes themselves are entered into a word vector model or with their POS tags attached. The morpheme vectors further vary depending on the consideration range of POS tags, the minimum frequency of morphemes included, and the random initialization range. All morpheme vectors are derived through CBOW(Continuous Bag-Of-Words) model with the context window 5 and the vector dimension 300. It seems that utilizing the same domain text even with a lower degree of grammatical correctness, performing spelling and spacing corrections as well as sentence splitting, and incorporating morphemes of any POS tags including incomprehensible category lead to the better classification accuracy. The POS tag attachment, which is devised for the high proportion of homonyms in Korean, and the minimum frequency standard for the morpheme to be included seem not to have any definite influence on the classification accuracy.

• Journal of Information Technology Services
• /
• v.17 no.1
• /
• pp.79-89
• /
• 2018

Sentiment analysis is a technique of text mining that extracts feelings of the person who wrote the sentence like movie review. The preliminary researches of sentiment analysis identify sentiments by using the dictionary which contains negative and positive words collected in advance. As researches on deep learning are actively carried out, sentiment analysis using deep learning model with morpheme or word unit has been done. However, this model has disadvantages in that the word dictionary varies according to the domain and the number of morphemes or words gets relatively larger than that of phonemes. Therefore, the size of the dictionary becomes large and the complexity of the model increases accordingly. We construct a sentiment analysis model using recurrent neural network by dividing input data into phoneme-level which is smaller than morpheme-level. To verify the performance, we use 30,000 movie reviews from the Korean biggest portal, Naver. Morpheme-level sentiment analysis model is also implemented and compared. As a result, the phoneme-level sentiment analysis model is superior to that of the morpheme-level, and in particular, the phoneme-level model using LSTM performs better than that of using GRU model. It is expected that Korean text processing based on a phoneme-level model can be applied to various text mining and language models.

• Journal of Information Science Theory and Practice
• /
• v.3 no.1
• /
• pp.6-23
• /
• 2015

This study develops an effective method for sentiment analysis of user-generated content on drug review websites, which has not been investigated extensively compared to other general domains, such as product reviews. A clause-level sentiment analysis algorithm is developed since each sentence can contain multiple clauses discussing multiple aspects of a drug. The method adopts a pure linguistic approach of computing the sentiment orientation (positive, negative, or neutral) of a clause from the prior sentiment scores assigned to words, taking into consideration the grammatical relations and semantic annotation (such as disorder terms) of words in the clause. Experiment results with 2,700 clauses show the effectiveness of the proposed approach, and it performed significantly better than the baseline approaches using a machine learning approach. Various challenging issues were identified and discussed through error analysis. The application of the proposed sentiment analysis approach will be useful not only for patients, but also for drug makers and clinicians to obtain valuable summaries of public opinion. Since sentiment analysis is domain specific, domain knowledge in drug reviews is incorporated into the sentiment analysis algorithm to provide more accurate analysis. In particular, MetaMap is used to map various health and medical terms (such as disease and drug names) to semantic types in the Unified Medical Language System (UMLS) Semantic Network.