• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1503-1516
• /
• 2019

In this paper, to improve the accuracy of long sentence similarity calculation, we proposed a sentence similarity calculation method based on a system similarity function. The algorithm uses word2vector as the system elements to calculate the sentence similarity. The higher accuracy of our algorithm is derived from two characteristics: one is the negative effect of penalty item, and the other is that sentence similar function (SSF) based on word2vector similar elements doesn't satisfy the exchange rule. In later studies, we found the time complexity of our algorithm depends on the process of calculating similar elements, so we build an index of potentially similar elements when training the word vector process. Finally, the experimental results show that our algorithm has higher accuracy than the word mover's distance (WMD), and has the least query time of three calculation methods of SSF.

• Speech Sciences
• /
• v.9 no.2
• /
• pp.49-58
• /
• 2002

This study is to classify intonation types of sentence terminal in accordance with sentence form in Korean dialects. Intonation types of sentence terminal in declarative, interrogative (yes-no and wh-sentence), imperative, suggestive of Gyeongnam dialect are low fall, high fall, high fall, low fall, so are not distinctive by intonation, but distinctive by final ending morphemes. But those of Jungbu dialect are low fall, rise-fall and full rise, high level, low rise-fall. Those of Jeonnam dialect are low level, rise-fall and full rise, high level, high level. So those of Jungbu dialect are similar to Jeonnam dialect.

• Phonetics and Speech Sciences
• /
• v.4 no.2
• /
• pp.127-134
• /
• 2012

The purpose of this study is to present evidence for a particular processing approach based on the language-specific characteristics of Korean. To compare individuals' sentence-comprehension abilities, this study measured the accuracy and reaction times (RT) of 12 aphasic patients (AP) and 12 normal controls (NC) during a sentence-picture matching task. Four versions of a sentence were constructed with the two types of voice (active/passive) and two types of word order (agent-first/patient-first). To examine the effects of increased processing demand, picture stimuli were manipulated in such a way that they appeared immediately after the sentence was presented. As expected, the AP group showed higher error rates and longer RT for all conditions than the NC group. Furthermore, Korean speakers with aphasia performed above a chance level in sentence comprehension, even with passive sentences. Aphasics understood sentences more quickly and accurately when they were given in the active voice and with agent-first order. The patterns of the NC group were similar. These results confirm that Korean adults with aphasia do not completely lose their knowledge of sentence comprehension. When the processing demand was increased by delaying the picture stimulus onset, the effect of increased processing demands on RT was more pronounced in the AP than in the NC group. These findings fit well with the idea that the computational system for interpreting sentences is intact in aphasics, but its ability is compromised when processing demands increase.

• MALSORI
• /
• no.35_36
• /
• pp.1-12
• /
• 1998

This study aims to investigate the prosodic characteristics of Korean discourse sentences, especially focusing the initial and final part of a sentence. 50 disourse sentences were read in two different styles; one, sentence by sentence, the other, continuous of all 50's. First, we tried to get two kinds of ratios from the acoustic results: first, ratio of the final syllable to the initial syllable in first word in a sentence; second, ratio of the final syllable to the initial syllable in last word in a sentence. We, then, calculated statistical values of the ratios including mean, standard deviation, minimum, maximum, and p-values in t-test. With respect to duration, there were little difference between two different styles. If any, we could see tiny unharmonious durational aspect in the initial of continuous reading. More concisely, there could be observed some deviation from standard. In case of F0, there was prominent statistical difference between ratios of last words in two styles. This difference might play a role as a prosodic feature. Energy seems to show similar pattern with that of F0. The results showed that final syllable in last word was pronounced with about 85 % of initial syllable in the same context and the last words in continuous speech were strongly articulated compared with those of sentence by sentence reading.

• The Journal of Korean Association of Computer Education
• /
• v.13 no.6
• /
• pp.79-89
• /
• 2010

In this paper, we proposed a method to find out similar sentences from documents to detect plagiarized documents. The proposed model adapts LSA and N-gram techniques to detect every type of Korean plagiarized sentence type. To evaluate the performance of the model, we constructed experimental data using students' essays on the same theme. Students made their essay by intentionally plagiarizing some reference documents. The experimental results showed that our proposed model outperforms the conventional N-gram model, Vector model, LSA model in precision, recall, and F measures.

• MALSORI
• /
• no.59
• /
• pp.27-51
• /
• 2006

For speech recognition systems, rejection function as well as decoding function is necessary to improve the reliability. There have been many research efforts on out-of-vocabulary word rejection, however, little attention has been paid on non-target sentence rejection. Recently pronunciation approaches using speech recognition increase the need for non-target sentence rejection to provide more accurate and robust results. In this paper, we proposed filler model method and word/phoneme detection ratio method to implement non-target sentence rejection system. We made performance evaluation of filler model along to word-level, phoneme-level, and sentence-level filler models respectively. We also perform the similar experiment using word-level and phoneme-level word/phoneme detection ratio method. For the performance evaluation, the minimized average of FAR and FRR is used for comparing the effectiveness of each method along with the number of words of given sentences. From the experimental results, we got to know that word-level method outperforms the other methods, and word-level filler mode shows slightly better results than that of word detection ratio method.

• Speech Sciences
• /
• v.2
• /
• pp.95-108
• /
• 1997

The purpose of this experimental study was to investigate prosodic characteristics of English as spoken by Koreans. Test materials were four English words, a sentence, and a paragraph. Six female Korean speakers and five native English speakers participated in acoustic and perceptual experiments. Pitch and duration of word syllables were measured from signals and spectrograms made by the Signalize 3.04 software program for Power Mac 7200. In the perceptual experiment, accent position, intonation patterns, rhythm patterns and phrasing were evaluated by the five native English speakers. Preliminary results from this limited study show that prosodic characteristics of Koreans include (1) pitch on the first part of a word and sentence is lower than that of English speakers, but the pitch on the last part is the opposite; (2) word prosody is quite similar to that of an English speaker, but sentence prosody is quite different; (3) the weakest point of sentence prosody spoken by Koreans is in the rhythmic pattern.

• Journal of the Korean Society for Library and Information Science
• /
• v.34 no.2
• /
• pp.87-115
• /
• 2000

The effects of the Case, Part of Speech, Word and Clause Location, Word Frequency etc. were studied in discriminating the similar sentences of the Korean text. Word Frequency was much related to the discrimination of similarity and Tilte word and Functional Clause were little, but the others were not. The cosine coefficient and Salton'similarity measurement are used to measure the similarity between sentences. The change of clauses between each sentence is also used to unify the similar sentences into a represenative sentence.

• Cross-Cultural Studies
• /
• v.19
• /
• pp.389-409
• /
• 2010

Chinese is a topic-prominent language, so when we learn Chinese we should know the discourse function of the Chinese language. Most of the Korean student think Chinese sentences should appear in the order of S-V-O and they always make mistakes when they use Chinese. I think Korean is very similar with Chinese in the discourse function. Hence, in this paper, I try to find a method of teaching Chinese topic sentence. It does so by comparing Chinese with Korean in the light of discourse function. I think when Korean student know how to use Korean topic sentence to explain the discourse functions of the Chinese language, they will not make similar mistakes. With this understanding in mind, chapter 2 tries to show various topic sentences to prove that 'topic' is very important in Chinese sentences. This is why we say Chinese is a topic-prominent language. In chapter 3, I analysis the sentences that students made, and highlight the reasons why they made mistake. The result lies in the reason whereby they always think Chinese should appear in the order of S-V-O. They do not understand why some sentences appear in the order of O-(S)V or S-O-V. It show that they do not know what is topic sentence and do not know how to make topic sentences. Sometime I have them translate them into Korean, but they also make Korean sentences like in the order of Chinese S-V-O. Therefore, I think, under this circumstance, to let them to translate and to speak in Korean in topic sentence, get some feelings about Chinese topic sentences, and tell and make Chinese topic sentences are naturally critical in their training.

• Journal of Korean Elementary Science Education
• /
• v.29 no.2
• /
• pp.134-143
• /
• 2010

The purpose of this study is to devise a new method for examining the readabilities of textbooks and to compare the readabilities of elementary school science textbooks. Third and sixth grade science textbooks were compared in terms of word, sentence, and paragraph in this study. In the word analyses, criterion suggested by Kim (2003) who classified about 238,000 words into seven categories according to their educational importances was adopted. In this study, the words from 3rd and 6th grade science textbooks were classified into four categories, and then the kinds and frequencies of words in each category were investigated. In the sentence analyses, sentences were classified either a simple sentence or a compound/complex sentence, and the ratios of each type were calculated. The average number of words in a sentence was also calculated in the sentence analyses. The ratios of conjunctions and demonstratives were examined in the paragraph analyses. The results indicated that both the kinds and frequencies of words in 3rd grade science textbook were smaller than those of 6th grade one. However, both science textbooks were similar in the distributions of words across the four categories. The ratio of simple sentences in 3rd grade science textbook was higher than that of 6th grade one, and the length of a sentence in 3rd grade science textbook was also shorter than that of 6th grade one. Both the ratios of conjunctions and demonstratives in 3rd grade science textbook were lower than those of 6th grade one.