• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.771-788
• /
• 2019

Deep learning techniques such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) show superior performance in text classification than traditional approaches such as Support Vector Machines (SVMs) and Naïve Bayesian approaches. When using CNNs for text classification tasks, word embedding or character embedding is a step to transform words or characters to fixed size vectors before feeding them into convolutional layers. In this paper, we propose a parallel word-level and character-level embedding approach in CNNs for text classification. The proposed approach can capture word-level and character-level patterns concurrently in CNNs. To show the usefulness of proposed approach, we perform experiments with two English and three Korean text datasets. The experimental results show that character-level embedding works better in Korean and word-level embedding performs well in English. Also the experimental results reveal that the proposed approach provides better performance than traditional CNNs with word-level embedding or character-level embedding in both Korean and English documents. From more detail investigation, we find that the proposed approach tends to perform better when there is relatively small amount of data comparing to the traditional embedding approaches.

• 한국컴퓨터정보학회논문지
• /
• 제11권5호
• /
• pp.75-86
• /
• 2006

일반적으로 영어를 한국어로 번역할 때, 대부분의 영어 명사 어휘들은 해당 어휘가 사용되는 문맥에 따라 다양한 한국어 명사로 번역될 수 있다. 따라서 영어 원문이 갖는 의미를 손실 없이 번역문으로 전달하기 위해서는 문맥에 맞는 올바른 한국어 대역어를 선택할 수 있어야 한다. 본 논문에서는 동사구패턴, 공기 정보에 기반한 의미벡터, 공기 품사 정보 및 한국어 문맥 통계 정보 등의 다양한 지식을 사용하여 영어 명사 어휘의 대역어를 올바로 선택하는 방안을 제공한다. 동사구 패턴은 사전과 코퍼스를 사용하여 구축되었으며, 의미 벡터는 영어 어휘가 특정 한국어 어휘로 번역될 때 공기하는 정보들의 조건부 확률을 나타낸다. 한국어 문맥 통계 정보는 한국어 코퍼스로부터 추출된 N-그램 정보를 나타내며, 품사 공기 정보는 대역어 선택 모호성을 지니는 영어 어휘와 통계적으로 깊은 관련성을 지니는 품사를 나타낸다. 마지막으로 본 논문에서 제안한 대역어 선택 모호성 해소 방안을 평가하기 위한 실험을 수행하였으며, 실험 결과, 제안하는 방법이 기존의 방법보다 성능이 좋다는 것을 확인할 수 있었다.

• 음성과학
• /
• 제9권1호
• /
• pp.77-88
• /
• 2002

Acoustical correlates of stress can be classified as duration, intensity and fundamental frequency. This study examined the acoustical differences in the first two syllables of stressed English words produced by ten American and Korean speakers. The Korean subjects scored very high on the TOEFL. They read at a normal speed a fable from which the acoustical parameters of eight words were analyzed. In order to make the data comparison meaningful, each parameter was collected at 100 dynamic time points proportional to the total duration of the two syllables. Then the ratio of the parameter sum of the first rime to that of the second rime was calculated to determine the relative prominence of the syllables. Results showed that the durations of the first two syllables were almost comparable between the Americans and Koreans. However, statistically significant differences showed up in the diphthong pronunciations and in the words with the second syllable stressed. Also, remarkably high r-squared values were found between pairs of the three acoustical parameters, which suggests that either one or a combination of two or more parameters may account for the prominence of a syllable within a word.

• 한국영어학회지:영어학
• /
• 제2권2호
• /
• pp.185-205
• /
• 2002

Within the framework of Generalized Sympathy (GS) (Jun 1999), this paper investigates the reasons why phonological rules such as Cluster Simplification, Closed Syllable ${\ae}$-Tensing, and Belfast Dentalization overapply or underapply in Class 2 affixed words in English. According to GS, a morphologically independent word can be treated as a derived word in that it is assumed to have any possible outputs as bases to resemble. As a result, a correspondence relation is triggered between a morphologically independent word being represented as Derived (D) and any possible outputs represented as Base (B), i.e., BD-Faith. In analyses of affixed words, BA-Faith is evoked, instead of BD-Faith. Furthermore, as Benua (1997) suggests, BA-Faith is classified into two correspondence relations; $BA_1$-Faith between Base and Class 1 affixed words, and $BA_2$-Faith between Base and Class 2 affixed words. When the $BA_1$-Faith takes precedence over phonological constraints three rules misapply in Class 2 affixed words. In other words, the misapplications are driven by base-identity effects.

• 말소리와 음성과학
• /
• 제4권2호
• /
• pp.33-40
• /
• 2012

The purpose of this paper is to investigate the voice onset time (VOT) of the English voiceless stops [p, t, k] found in the Buckeye Corpus of Conversational Speech [1]. Three young female speakers were chosen for this study and their VOT values were semi-automatically extracted along with other factors. The factors used for the analysis were place of articulation, location in word, syllabic stress, content word or not, word frequency calculated from the corpus, and the speech rate expressed in syllables per second. Results showed that, for the three places of articulation of each speaker, all the factors had a statistically significant effect on the VOT values. This paper has significance in that the materials used for the analysis were from a corpus of spontaneous natural English speech.

• 음성과학
• /
• 제7권4호
• /
• pp.169-186
• /
• 2000

This paper aims to confirm the mispronunciation of native Korean students due to the phonetic and phonological system differences between English and Korean, and to find the works-to-do by experiment. Many Korean students tend to differentiate the sounds of word-final stop consonants not by vowel duration or the allophones but by the phoneme of the consonant itself. In English, Stop sounds change through the conditions of the aspirated, unaspirated, or unreleased sounds. But in Korean they are not allophones of phonemes but distinct phonemes. Therefore, many Korean students are apt to add an extra vowel sound /i/ after the final stop consonant in the eve form due to both the unperception of the differences between the phonemes and the allophones of stop consonants, and the influence of the Korean sound-sequence relationship. Since the replacement of the allophones and extra vowel addition does not change the meaning, the importance was almost lost. Nevertheless, this kind of study is essential for the precise learning and the use of the English language.

• 말소리와 음성과학
• /
• 제8권1호
• /
• pp.9-17
• /
• 2016

The purpose of this work is to examine the voice onset times(VOTs) of the voiceless and voiced stops from the ten young male speakers of the Buckeye corpus[9]. The factors that are known to affect VOTs were also extracted, including the place of articulation, height of following vowels, location within word, presence of a preceding [s], status of the target word with respect to the content versus function word, presence of a syllabic stress, word frequency and speech rate. Findings from this work mostly agreed with those from earlier studies on English, but with some exceptions and new discoveries. We hope that this work can contribute to figuring out the nature and properties of the spontaneous speech of English.

• 말소리와 음성과학
• /
• 제5권3호
• /
• pp.31-38
• /
• 2013

This study investigated the influence of English vowel pronunciation training to English word-initial stop pronunciation. For that purpose, VOT values of English stops produced by twenty Korean English learners(five Youngnam dialect male speakers, five Youngnam dialect female speakers, five Kangwon dialect male speakers, and five Kangwon dialect female speakers) were measured using the Speech Analyzer and their post-training production was compared with their pre-training production. The result shows that post-training VOT values of voiced stops became closer to those of native English speakers in all four groups. Hence, it can be inferred that vowel pronunciation training is effective for correcting pronunciation of voiced vowels by analyzing the change of the quality of following vowels(especially low vowels) and the degree of giving stress.

• 대한음성학회지:말소리
• /
• 제44호
• /
• pp.1-14
• /
• 2002

Because the accuracy and the fluency are the essence in English speaking, both of them are very important in English trencher training and in-service English training programs. To get the accuracy and the fluency, the causes and the phenomena of the unnatural pronunciation have to be diagnosed. Consequently, the problematic and unnatural pronunciation of Korean elementary and secondary English teachers should be analyzed with using Acoustic Analyzing tools like CSL, Multi-speech and Praat. In addition, an attempt to Pinpoint what the causes of unnatural pronunciation was executed. Next a procedure and steps were proposed for in-service training programs that would cultivate the fluency and the accuracy. In case of elementary teachers, the unnatural pronunciation of segmental features and suprasegmental features were found much. therefore segmental features should be emphasized in the begging of pronunciation training courses and then suprasegmental features have to be emphasized. In case of secondary teachers, the unnatural pronunciation of suprasegmental features were found much. Therefore segmental and suprasegmental features have to be focused at the same time. In other words, features in word level should be focused first for elementary English teacher, and features in word level and beyond word level should be trained at the same time for secondary English teachers.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.521-524
• /
• 2009

인터넷 환경의 급속하게 발전하면서 웹을 통하여 많은 학습 매체를 경험할 수 있다. 특히 영어 교육의 중요성이 강조되면서, 많은 영어 학습 관련 소프트웨어가 출시되었다. 그러나 기존 영어단어 교육용 시스템은 대부분 1명의 사용자가 게임을 진행하는 방식이며, 또한 'WIKIPEDIA'와 같은 신조어를 전혀 고려하지 못한다. 따라서 본 논문에서는 사용자에게 흥미와 즐거움을 유도하여 학습이 가능하도록 '스크레블'이라는 보드게임을 온라인으로 구현하였다. 제안하는 영어단어 교육용 게임시스템의 특징은 다음과 같다. 첫째, 제안하는 시스템은 인공지능을 바탕으로 한 가상의 사용자와 함께 단일 사용자 모드와 다중 사용자 모드를 모두 지원한다. 둘째, 제안하는 시스템은 NEVER 오픈 API사전을 이용하여 'WIKIPEDIA'와 같은 신조어에도 인식할 수 있다. 셋째, 매뉴얼 없이도 쉽게 게임을 즐길 수 있도록 사용자에게 익숙한 UI를 제공한다. 따라서 제안하는 시스템은 사용자에게 영어단어학습에 대한 흥미와 즐거움을 고취할 수 있다고 기대한다.