• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.107-116
• /
• 2004

This paper introduces ISAAC (An Interface for Sentence Analysis & Abstraction with Cogitation) which provides an integrated user interface for sentence analysis. Into ISAAC, the various linguistic tools and resources are integrated. They are necessary for sentence analysis. Most of the tools and resources for sentence analysis are developed and accumulated independently. In the sentence analyzing with these tools and resources, it is difficult for sentence analyst to manage and control information which is taken on each step. In this respect, we have integrated the usable tools and resources, and made ISAAC to provide the consistent user oriented interface to each function. We have been able to divide sentence analysis process Into 14 steps. In ISAAC, these steps are processed by four individual modules $\cicled1$syntactic analysis of sentence,$\cicled2$retrieval of a root word,$\cicled3$searching category information in Roget s Thesaurus, and $\cicled4$searching category information in OfN(Ontology for Narratives). Therefore, in case of sentence analysis with ISAAC, the process of total 14 steps falls into 4 steps. This means that it is able to improve the performance of sentence analyst to the extent 3.5 times or more. Furthermore, ISAAC undertaking tedious transcription needed to process each step, we expect that ISAAC can help the analyst to maintain the accuracy of sentence analysis.

• Phonetics and Speech Sciences
• /
• v.6 no.3
• /
• pp.131-138
• /
• 2014

A close-copy stylization of intonation curve was used for an acoustical analysis of emotional speech. For the analysis, 408 utterances of five emotions (happiness, anger, fear, neutral and sadness) were processed to extract acoustical feature values. The results show that certain pitch point features (pitch point movement time and pitch point distance within a sentence) and sentence level features (pitch range of a final pitch point, pitch range of a sentence and pitch slope of a sentence) are affected by emotions. Pitch point movement time, pitch point distance within a sentence and pitch slope of a sentence show no significant difference between male and female participants. The emotions with high arousal (happiness and anger) are consistently distinguished from the emotion with low arousal (sadness) in terms of these acoustical features. Emotions with higher arousal show steeper pitch slope of a sentence. They have steeper pitch slope at the end of a sentence. They also show wider pitch range of a sentence. The acoustical analysis in this study implies the possibility that the measurement of these acoustical features can be used to cluster and identify emotions of speech.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.10
• /
• pp.38-47
• /
• 1998

The syntactic analysis for the practical machine translation should be able to analyze a long sentence, but the long sentence analysis is a critical problem because of its high analysis complexity. In this paper a sentence segmentation method is proposed for an efficient analysis of a long sentence and the method of determining optimal sentence segmentation positions using statistical information and genetic learning is introduced. It consists of two modules: (1) decomposable position determination which uses lexical contextual constraints acquired from a training data tagged with segmentation positions. (2) segmentation position selection by the selection function of which the weights of parameters are determined through genetic learning, which selects safe segmentation positions with enhancing the analysis efficiency as much as possible. The safe segmentation by the proposed sentence segmentation method and the efficiency enhancement of the analysis are presented through experiments.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.39-46
• /
• 2021

This study is about a method of extracting a summary from a news article in consideration of the importance of each sentence constituting the article. We propose a method of calculating sentence importance by extracting the probabilities of topic sentence, similarity with article title and other sentences, and sentence position as characteristics that affect sentence importance. At this time, a hypothesis is established that the Topic Sentence will have a characteristic distinct from the general sentence, and a deep learning-based classification model is trained to obtain a topic sentence probability value for the input sentence. Also, using the pre-learned ELMo language model, the similarity between sentences is calculated based on the sentence vector value reflecting the context information and extracted as sentence characteristics. The topic sentence classification performance of the LSTM and BERT models was 93% accurate, 96.22% recall, and 89.5% precision, resulting in high analysis results. As a result of calculating the importance of each sentence by combining the extracted sentence characteristics, it was confirmed that the performance of extracting the topic sentence was improved by about 10% compared to the existing TextRank algorithm.

• Speech Sciences
• /
• v.14 no.1
• /
• pp.121-135
• /
• 2007

The purpose of this paper is to examine how Korean speakers realize English stress and rhythm at the sentence level, and investigate what different acoustic characteristics of English sentence stress and rhythm Korean speakers have, compared with those of American English speakers. Stressed words in the sentence were analyzed in terms of duration, fundamental frequency, and intensity of the stressed vowel in the word with neutral stress and with emphatic stress, respectively. According to the results, when the words had emphatic stress, both Koreans' and Americans' F0 and intensity of the stressed vowel were higher than those with neutral stress. Korean speakers of English realized the sentence stress with shorter vowel duration and higher F0 than American English speakers when the words had emphatic stress. The analysis of the timing of the sentence with increased unstressed syllables showed that both Americans and Koreans produced the sentence with longer duration as the number of unstressed syllables increased. However, the duration of unstressed syllables between stressed syllables by Koreans was longer than that by Americans. Americans seemed to produce unstressed syllables between stressed syllables faster than Koreans for regular intervals of stressed syllables. This analysis implies that if there are more unstressed syllables between stressed syllables, Koreans might produce unstressed syllables and the whole sentence with longer duration.

• Education of Primary School Mathematics
• /
• v.14 no.3
• /
• pp.293-302
• /
• 2011

The objective of this study is to search the recognition of teacher on the pattern and characteristics of the questioning sentence of the newly appointed teachers for the mathematics class through the case study for the 2ndyear teachers. The study participants' class was recorded in video and individual interview was made for 4 times. The pattern of the questioning sentence in the observed class was analyzed using the classification frame with addition of creativity related items to the classification frame suggested by Mogan & Saxton(2006). The questioning sentence and recognition on the mathematics class for the newly appointed teachers were analyzed based on the individual meeting and class materials. In result, the questioning sentence for confirmation was most frequent (69%) and questioning sentence of understanding (25%) and the questioning sentence for introspection (6%) in its priority. It was known that the questioning sentence for extending the creativity didn't make it at all. It was revealed that the participant teachers in this study used the questioning sentence pattern for fact confirmation of the student most frequently and the use of the questioning sentence for accelerating the creative thinking of the student was lacked. In addition, the teachers recognized that they manage the class oriented to questioning sentence for obtaining the concept. It was known that the education for the questioning sentence which accelerates the creativity and other thinking as well as the fact confirmation pattern is necessary through the training for the new teachers in the future.

• Journal of Elementary Mathematics Education in Korea
• /
• v.12 no.2
• /
• pp.185-204
• /
• 2008

The purposes of this study are to analyze sentence structures of word problems suggested in educational math programs for the 2nd grade elementary students and error patterns in sentence interpretation, and examine how sentence structures influence on errors during sentence comprehension. Based on the results of the analysis on 168 word problems suggested in math textbooks for the 2nd grade elementary students and error patterns observed while 160 the 2nd grade elementary students attempted to solve math word problems, easy and simple vocabularies are repeatedly used in the sentence structures of word problems and specific real life materials such as fruits, books, the number of people and etc. were repeatedly used. 51.56% of errors in sentence interpretation observed was higher than 39.20% of calculation errors and backtracking operation, a length of sentences, the numbers used in questions and off were analyzed to be involved in the errors in interpretation. Therefore, it is very important to make word problems from a student's points of view rather than a teacher's point of view and the study suggests that teachers help students learn basic sentence interpretation skills.

• The Journal of the Korea Contents Association
• /
• v.12 no.9
• /
• pp.9-15
• /
• 2012

A conventional event sentence extraction research doesn't learn the 3W features in the learning step and applies the rule on whether the 3W feature exists in the extraction step. This paper presents a sentence weight based event sentence extraction method that calculates the weight of the 3W features in the learning step and applies the weight of the 3W features in the extraction step. In the experimental result, we show that top 30% features by the $TF{\times}IDF$ weighting method is good in the feature filtering. In the real estate domain of the public issue, the performance of sentence weight based event sentence extraction method is improved by who and when of 3W features. Moreover, In the real estate domain of the public issue, the sentence weight based event sentence extraction method is better than the other machine learning based extraction method.

• Korean Journal of Computational Design and Engineering
• /
• v.21 no.4
• /
• pp.433-442
• /
• 2016

This paper aims to define the relational logic of in-between code articles as well as within atomic sentences in Korean Building Code, as an intermediate research and development process for the automated building permit system of Korea. The approach depicted in this paper enables the software developers to figure out the logical relations in order to compose KBimCode and its databases. KBimCode is a computer-readable form of Korean Building Code sentences based on a logic rule-based mechanism. Two types of relational logic definition are described in this paper. First type is a logic definition of relation between code sentences. Due to the complexity of Korean Building code structure that consists of decree, regulation or ordinance, an intensive analysis of sentence relations has been performed. Code sentences have a relation based on delegation or reference each other. Another type is a relational logic definition in a code sentence based on translated atomic sentence(TAS) which is an explicit form of atomic sentence(AS). The analysis has been performed because the natural language has intrinsic ambiguity which hinders interpreting embedded meaning of Building Code. Thus, both analyses have been conducted for capturing accurate meaning of building permit-related requirements as a part of the logic rule-based mechanism.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.16-24
• /
• 2021

The exiting word embedding methodology such as word2vec represents words, which only occur in the raw training corpus, as a fixed-length vector into a continuous vector space, so when mapping the words incorporated in the raw training corpus into a fixed-length vector in morphologically rich language, out-of-vocabulary (OOV) problem often happens. Even for sentence embedding, when representing the meaning of a sentence as a fixed-length vector by synthesizing word vectors constituting a sentence, OOV words make it challenging to meaningfully represent a sentence into a fixed-length vector. In particular, since the agglutinative language, the Korean has a morphological characteristic to integrate lexical morpheme and grammatical morpheme, handling OOV words is an important factor in improving performance. In this paper, we propose parallel Tri-LSTM sentence embedding that is robust to the OOV problem by extending utilizing the morphological information of words into sentence-level. As a result of the sentiment analysis task with corpus in Korean, we empirically found that the character unit is better than the morpheme unit as an embedding unit for Korean sentence embedding. We achieved 86.17% accuracy on the sentiment analysis task with the parallel bidirectional Tri-LSTM sentence encoder.