• Title/Summary/Keyword: Natural Language Understanding

Search Result 129, Processing Time 0.028 seconds

A Study of Fundamental Frequency for Focused Word Spotting in Spoken Korean (한국어 발화음성에서 중점단어 탐색을 위한 기본주파수에 대한 연구)

  • Kwon, Soon-Il;Park, Ji-Hyung;Park, Neung-Soo
    • The KIPS Transactions:PartB
    • /
    • v.15B no.6
    • /
    • pp.595-602
    • /
    • 2008
  • The focused word of each sentence is a help in recognizing and understanding spoken Korean. To find the method of focused word spotting at spoken speech signal, we made an analysis of the average and variance of Fundamental Frequency and the average energy extracted from a focused word and the other words in a sentence by experiments with the speech data from 100 spoken sentences. The result showed that focused words have either higher relative average F0 or higher relative variances of F0 than other words. Our findings are to make a contribution to getting prosodic characteristics of spoken Korean and keyword extraction based on natural language processing.

Proposing a Simple Radiation Scale for the Public: Radiation Index

  • Cho, Gyuseong;Kim, Jong Hyun;Park, Tae Soon;Cho, Kunwoo
    • Nuclear Engineering and Technology
    • /
    • v.49 no.3
    • /
    • pp.598-608
    • /
    • 2017
  • A new radiation scale is proposed. With empathy toward the vast majority of people who are not well versed in radiation and related matters, and thus suffering from misunderstanding that breeds unnecessary fear of radiation, the aim of proposing a new radiation scale, radiation index (RAIN), is to put the general public at ease with the concept of radiation. RAIN is defined in dimensionless numbers that relate any specific radiation dose to a properly defined reference level. As RAIN is expressed in plain numbers without an attached scientific unit, the public will feel comfortable with its friendly look, which in turn should help them understand radiation dose levels easily and allay their anxieties about radiation. The expanded awareness and proper understanding of radiation will empower the public to feel that they are not hopeless victims of radiation. The correspondence between RAIN and the specific accumulated dose is established. The equivalence will allow RAIN to serve as a common language of communication for the general public with which they can converse with radiation experts to discuss matters related to radiation safety, radiation diagnosis and therapy, nuclear accidents, and other related matters. Such fruitful dialogues will ultimately enhance public acceptance of radiation and associated technologies.

Use Case Elicitation Method Using "When" Sentences from User Reviews

  • Kim, Neung-Hoe;Hong, Chan-Ki
    • International journal of advanced smart convergence
    • /
    • v.9 no.4
    • /
    • pp.198-202
    • /
    • 2020
  • User review sites are spaces where users can freely post and share their opinions, which are trusted by many people and directly influence sales. In addition, they overcome the limitations arising from existing requirements collection and are able to gather the needs of large numbers of different people at a low cost. Therefore, such sites are attracting attention as new spaces for understanding user needs. In a previous study, a user review analysis was attempted using 5W and 1H, and we inferred that a sentence containing "when" has special information based on the user experience. In addition, the requirements of the derivative activities in a user review can identify more user needs than the general requirements of derivative activities. In this paper, we propose a systematic method of deriving "when" sentences contain meaningful information from user reviews and converting them into use cases, which is one of the requirements of a specification method. This method converts unstructured data into structured data such that it can be included as the user requirements during software development from user comments expressed in natural language. This method will reduce project failures and increase the likelihood of success by enabling an efficient collection and analysis of user needs from valuable user reviews.

Untold story about why King Sejong invented the Korean alphabet

  • JUNG, Sanggyu
    • Journal of Koreanology Reviews
    • /
    • v.1 no.1
    • /
    • pp.1-23
    • /
    • 2022
  • HunMinJeongEum, meaning "the right sound to teach the people," was created in 1443 CE by King Sejong the Great, the fourth king of the Joseon Dynasty. In today's modern language, this letter, called Hangeul, is internationally recognized for its linguistic science. However, it is hard to find a comprehensive study on the fact that King Sejong himself created Hangeul, the Confucian perspective on natural disasters and democracy revealed in the process of writing, the independent efforts emphasized from a certain period, and the achievements of King Sejong, who shared the sorrow of the people and carried out national policies despite the extreme opposition of the nobility. Accordingly, I analyzed the consonants of HunMinJeongEum and looked at the essence of humanity and oriental philosophy (Yin-Yang Five Elements, Sangsu Philosophy, Hado). Surprisingly, different meanings from previous studies and interpretations were found, and King Sejong's "Da Vinci Code," which was left behind in the process of making the consonant, is reinterpreted and revealed. King Sejong's achievements were all connected as one. This is the root of democracy in the Republic of Korea today, and this is why King Sejong was selected as the most beloved and respected historical figure by the Korean people. This study will start with more people's understanding of the fundamental perception and philosophy of the world in Asia, including Korea, to reinterpret and reveal the hardships and great achievements experienced by a leader of a country in the process of creating korean alphabet, and to emphasize democracy, which is an important value for Asians and Westerners' mutual respect and co-prosperity.

Understanding Sexual Identity-related Concerns through the Analysis of Questions on a Social Q&A Site (소셜 Q&A 사이트의 질문 분석을 통한 청소년의 성 정체성(sexual identity) 고민에 대한 이해)

  • Zhu, Yongjun;Nam, Seojin;Yi, Dajeong;Yi, Yong Jeong
    • Journal of Korean Library and Information Science Society
    • /
    • v.51 no.4
    • /
    • pp.101-119
    • /
    • 2020
  • The study aims to understand major topics and concerns of gender identity-related questions expressed by the users of the NAVER social Q&A site. To achieve this goal, we analyzed 2,120 questions created from 2010 to 2018 using natural language- and information retrieval-based methods. Results indicated that the major topics discussed by the users include interpersonal relationships, doubts about gender identity, sexual orientation, feelings and relationships, and concerns about gender identity. In addition, users mainly expressed concerns regarding general issues of gender identity; sexual orientation; negative cognition about gender identity; confession, coming-out, homosexuality; future, heterosexual relationships, military enlistment; and causes of gender identity confusion. The present study effectively derives information needs from real-world concerns about sexual identity by employing topic modeling techniques, and by comparing the advantages of exact match and tf-idf-based information retrieval methods extends methodology of Library and Information Science. Further, it has contributed to the academic maturity of the study of information behavior by observing the information needs or information-seeking behaviors of online community users with specific interests.

Spatialization of Unstructured Document Information Using AI (AI를 활용한 비정형 문서정보의 공간정보화)

  • Sang-Won YOON;Jeong-Woo PARK;Kwang-Woo NAM
    • Journal of the Korean Association of Geographic Information Studies
    • /
    • v.26 no.3
    • /
    • pp.37-51
    • /
    • 2023
  • Spatial information is essential for interpreting urban phenomena. Methodologies for spatializing urban information, especially when it lacks location details, have been consistently developed. Typical methods include Geocoding using structured address information or place names, spatial integration with existing geospatial data, and manual tasks utilizing reference data. However, a vast number of documents produced by administrative agencies have not been deeply dealt with due to their unstructured nature, even when there's demand for spatialization. This research utilizes the natural language processing model BERT to spatialize public documents related to urban planning. It focuses on extracting sentence elements containing addresses from documents and converting them into structured data. The study used 18 years of urban planning public announcement documents as training data to train the BERT model and enhanced its performance by manually adjusting its hyperparameters. After training, the test results showed accuracy rates of 96.6% for classifying urban planning facilities, 98.5% for address recognition, and 93.1% for address cleaning. When mapping the result data on GIS, it was possible to effectively display the change history related to specific urban planning facilities. This research provides a deep understanding of the spatial context of urban planning documents, and it is hoped that through this, stakeholders can make more effective decisions.

A study on the Development of Physics Education Program for Foreign Students of Natural Science and Engineering College in Korea (이공계 대학의 유학생을 위한 물리교육 프로그램 개발 연구)

  • Kim, Soocheol
    • Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
    • /
    • v.9 no.9
    • /
    • pp.1-16
    • /
    • 2019
  • This study was carried out to develop a physics education program for foreign students of university in Korea to improve their ability to major in the field and to prevent them from becoming dropout. The subjects of the study are five Chinese students attending a natural science and engineering college. Prior to the development of the physics education program, the researchers developed basic physics textbooks for the foreign students and questionaries for diagnosis and summative evaluation, and utilized them to apply a total of seven classes. After the application of the classes, the results of the student's diagnosis and summative evaluation, the teacher's diaries, the observer's diaries, and the transcripts were analyzed by triangulation method. In addition, Nvivo12 was used for the analysis of the teacher's and observer's diaries to help with qualitative analysis. The results of the study are as follows: First, the oder and contents of physics education program for students of the natural science and engineering college were presented in detail, and basic physics textbooks and tools for diagnosis and summative assessment were developed. Second, as a result of the analysis of the diagnosis and summative assessment results of the program, the students' basic physics achievement improved by an average of 40 points due to the application of the developed program. Third, as a result of the application of the program using Nvivo12, meaningful node and actual cases were extracted. There were 10 types of nodes created such as understanding of the students, teaching method, rate of the participation, level differences, language problems, relevance to majors, curriculum and methods of education in the country of origin, cooperative learning, and interest inducement. The researcher provided suggestions on physics education methods for students of science and engineering colleges in Korea based on the related cases.

Exploring the Foreign Students' Learning Experiences in Natural Science Basic Course at College of Engineering in Korea (국내 이공계 대학 유학생들의 전공기초 학습 경험 탐색)

  • Kim, Soo-Cheol
    • Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
    • /
    • v.9 no.2
    • /
    • pp.259-269
    • /
    • 2019
  • The main purpose of this study is to explore the foreign students' learning experiences in natural science basic course at college of engineering in Korea. The subjects were 7 but 4 students took part in the semi-structured interview. All of the interviews were recorded, and the recorded material was transferred and kept. The transcripts were analyzed in a qualitative method. The researchers answered the questionnaire to 7 foreign students who voluntarily participated in the study, and 4 in-depth interviews were also conducted. The interview took 30 minutes to 1 hour, and semi - structured interviewing technique was used. The contents of the interviews were all recorded with the consent of the participants, and the recorded materials were transferred and managed with the interview notes. The transferred data were analyzed based on the coding and categorization process according to the step of the continuous comparison method. The results of this study is the following. There are four themes; problems due to lack of Korean language ability when taking basic courses; problems of terms and concept understanding in major courses; supplementary learning methods of basic courses; necessity of natural science basic education program and requirement of support of the university.

The Marital Conflicts and Coping Strategies in the Multicultural Families (다문화가족의 부부갈등과 갈등대처전략)

  • Hong, Sung-Hee
    • Journal of Family Resource Management and Policy Review
    • /
    • v.16 no.1
    • /
    • pp.149-175
    • /
    • 2012
  • The purpose of this study is to find out marital conflicts and coping strategies among married female immigrants and Korean men in multicultural families. The data were collected by in.depth interviews with 12 female immigrants and 5 Korean men. The major findings of this study are as follows: Female participants suffered from marital conflicts with their spouses, conflicts with mothers.in.law, stereotyped gender roles as a wife and a daughter.in.law, economic conflicts, and cultural differences between Korea and their country. In addition, male participants reported conflicts from economic support for their wife's family, gender role differences, and cultural differences. Coping strategies used to deal with the conflicts, such as mutual dedication and understanding their spouse's stance, and developing a compromise for the family's happiness were mentioned. A personal positive nature and attitude helped them to meet the marital conflicts. Supports from their husband, parents.in.law, and society also helped female immigrants to adapt to cultural differences. However, some of them used negative coping strategies which did not reduce conflicts, and resulted in separation and divorce. The coping strategies to deal with the conflicts depended on the participants' personal ability. While female participants who had English language skills took advantage to adapt to Korean society, those who did not have any other natural abilities could develop a definite position in their family and society with their diligence and positive attitude. The results showed that female participants who were supported by their family and society tended to cope successfully with conflicts and also showed that multicultural families' marital adjustment was maintained with their efforts as well as by relationships with their relatives and society.

  • PDF

Semantic Image Retrieval Using Color Distribution and Similarity Measurement in WordNet (컬러 분포와 WordNet상의 유사도 측정을 이용한 의미적 이미지 검색)

  • Choi, Jun-Ho;Cho, Mi-Young;Kim, Pan-Koo
    • The KIPS Transactions:PartB
    • /
    • v.11B no.4
    • /
    • pp.509-516
    • /
    • 2004
  • Semantic interpretation of image is incomplete without some mechanism for understanding semantic content that is not directly visible. For this reason, human assisted content-annotation through natural language is an attachment of textual description to image. However, keyword-based retrieval is in the level of syntactic pattern matching. In other words, dissimilarity computation among terms is usually done by using string matching not concept matching. In this paper, we propose a method for computerized semantic similarity calculation In WordNet space. We consider the edge, depth, link type and density as well as existence of common ancestors. Also, we have introduced method that applied similarity measurement on semantic image retrieval. To combine wi#h the low level features, we use the spatial color distribution model. When tested on a image set of Microsoft's 'Design Gallery Line', proposed method outperforms other approach.