• The Journal of the Acoustical Society of Korea
• /
• v.26 no.1E
• /
• pp.1-7
• /
• 2007

One result of the trend towards globalization is an increased number of projects that focus on natural language processing. Automatic speech recognition (ASR) technologies, for example, hold great promise in facilitating global communications and collaborations. Unfortunately, to date, most research projects focus on single widely spoken languages. Therefore, the cost to adapt a particular ASR tool for use with other languages is often prohibitive. This work takes a more general approach. We propose an International Phoneticizing Engine (IPE) that interprets input files supplied in our Phonetic Language Identity (PLI) format to build a dictionary. IPE is language independent and rule based. It operates by decomposing the dictionary creation process into a set of well-defined steps. These steps reduce rule conflicts, allow for rule creation by people without linguistics training, and optimize run-time efficiency. Dictionaries created by the IPE can be used with the Sphinx speech recognition system. IPE defines an easy-to-use systematic approach that can lead to internationalization of automatic speech recognition systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1778-1799
• /
• 2022

Automatic text summarization is a procedure that packs enormous content into a more limited book that incorporates significant data. Malayalam is one of the toughest languages utilized in certain areas of India, most normally in Kerala and in Lakshadweep. Natural language processing in the Malayalam language is relatively low due to the complexity of the language as well as the scarcity of available resources. In this paper, a way is proposed to deal with the text summarization process in Malayalam documents by training a model based on the Support Vector Machine classification algorithm. Different features of the text are taken into account for training the machine so that the system can output the most important data from the input text. The classifier can classify the most important, important, average, and least significant sentences into separate classes and based on this, the machine will be able to create a summary of the input document. The user can select a compression ratio so that the system will output that much fraction of the summary. The model performance is measured by using different genres of Malayalam documents as well as documents from the same domain. The model is evaluated by considering content evaluation measures precision, recall, F score, and relative utility. Obtained precision and recall value shows that the model is trustable and found to be more relevant compared to the other summarizers.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.390-396
• /
• 2008

Storybooks, especially those for children, may contain illustrations. An automated system for generating illustrations would help the production process of storybook publishing. In this paper, we propose a method for automatically generating layouts of objects during generating illustrations. In generated layouts, it is preferred to avoid unnecessary overlap between objects, corresponding to the spatial information in storybooks. We first define a representation scheme for spatial information in natural language sentences using tree structures and predicate-argument structures. Unification of tree structures and Region Connection Calculus are then used to manipulate the information and generate corresponding illustrations.

• KIISE Transactions on Computing Practices
• /
• v.22 no.5
• /
• pp.218-224
• /
• 2016

This paper proposes a computer-based practical automatic scoring system for Korean short answers through student answer analysis and natural language processing techniques. The proposed system reduces the overall scoring time and budget, while improving the ease-of-use to write answer templates from student answers as well as the accuracy and reliability of automatic scoring system. To evaluate the application of the automatic scoring system and compare to the human scoring process, we performed an experiment using the student answers of social science subject in 2014 National Assessment of Educational Achievement.

• Journal of Digital Convergence
• /
• v.17 no.11
• /
• pp.517-522
• /
• 2019

In many businesses, chatbots enhance the user experience by providing the most immediate and direct feedback to user questions. The area of use of chatbots is growing. In this study, the three types of chatbot definition, command method, function, and platform are classified according to their distinct factors. In the process, the functional delimiter element is necessary for the Chatbot UX, which is a key technical element of the functional part of pattern recognition, natural language processing, semantic web, text mining, and context-aware computing. However, the limitations at this stage were also known. Based on this, we analyzed the chatbot's UX elements for Facebook, Skype, Telegram, and Google Assistant for a better user experience. Basic UI elements such as cards, quick response, command, and application of persistent menus are needed as user experience elements.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.284-291
• /
• 2022

Historical data from comparable projects can serve as benchmarking data for an ongoing project's planning during the project scoping phase. As project owners typically store substantial amounts of data generated throughout project life cycles in digitized databases, they can capture appropriate data to support various project planning activities by accessing digital databases. One of the most important work tasks in this process is identifying one or more past projects comparable to a new project. The uniqueness and complexity of construction projects along with unorganized data, impede the reliable identification of comparable past projects. A project scope document provides the preliminary overview of a project in terms of the extent of the project and project requirements. However, narratives and free-formatted descriptions of project scopes are a significant and time-consuming barrier if a human needs to review them and determine similar projects. This study proposes an Artificial Intelligence-driven model for analyzing project scope descriptions and evaluating project similarity using natural language processing (NLP) techniques. The proposed algorithm can intelligently a) extract major work activities from unstructured descriptions held in a database and b) quantify similarities by considering the semantic features of texts representing work activities. The proposed model enhances historical comparable project identification by systematically analyzing project scopes.

• International conference on construction engineering and project management
• /
• 2013.01a
• /
• pp.60-65
• /
• 2013

Introducing the concept of construction safety in the design/engineering phase can improve the efficiency and effectiveness of safety management on construction sites. In this sense, further improvements for safety can be made in the design/engineering phase through the development of (1) an automated hazard identification process that is little dependent on user knowledge, (2) an automated construction schedule generation to accommodate varying hazard information over time, and (3) a visual representation of the results that is easy to understand. In this paper, we formulate an automated hazard identification framework for construction safety by extracting hazard information from related regulations to eliminate human interventions, and by utilizing a visualization technique in order to enhance users' understanding on hazard information. First, the hazard information is automatically extracted from textual safety and health regulations (i.e., Occupational Safety Health Administration (OSHA) Standards) by using natural language processing (NLP) techniques without users' interpretations. Next, scheduling and sequencing of the construction activities are automatically generated with regard to the 3D building model. Then, the extracted hazard information is integrated into the geometry data of construction elements in the industry foundation class (IFC) building model using a conformity-checking algorithm within the open source 3D computer graphics software. Preliminary results demonstrate that this approach is advantageous in that it can be used in the design/engineering phases of construction without the manual interpretation of safety experts, facilitating the designers' and engineers' proactive consideration for improving safety management.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.721-724
• /
• 2018

최근 청소년들은 욕설, 폭력적, 선정적, 비하적 표현을 일상생활에서 자연스럽게 사용하고 있다. 현재 청소년들은 자극적이고 폭력적인 개인 방송을 시청하며 유해 표현을 학습한다. 그래서 여러 기업에서는 모니터링 요원을 배치하거나 사용자들의 신고를 통해 유해 영상을 제재하는 중이다. 하지만 방대한 규모의 동용상 때문에 사람이 직접 모든 영상을 확인하는 것은 물리적으로 불가능하다. 따라서 본 논문에서는 자연어 처리 기술을 활용하여 자동으로 유해 영상을 탐지하는 시스템을 제안하고자 한다. 본 시스템은 데이터 수집, 텍스트 변환, 형태소 분석, 유해 사전 구성, 유해 판단 5가지 과정으로 이루어진다.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.69-80
• /
• 2021

Neural machine translation using deep neural network has emerged as a mainstream research, and an abundance of investment and studies on model structure and parallel language pair have been actively undertaken for the best performance. However, most recent neural machine translation studies pass along decoding strategy to future work, and have insufficient a variety of experiments and specific analysis on it for generating language to maximize quality in the decoding process. In machine translation, decoding strategies optimize navigation paths in the process of generating translation sentences and performance improvement is possible without model modifications or data expansion. This paper compares and analyzes the significant effects of the decoding strategy from classical greedy decoding to the latest Dynamic Beam Allocation (DBA) in neural machine translation using a sequence to sequence model.

• Journal of The Korean Association of Information Education
• /
• v.26 no.3
• /
• pp.197-207
• /
• 2022

In this paper, we develop a machine learning based block code generation and recommendation model for the purpose of reducing cognitive load of learners during coding education that learns the learner's block that has been made in the block programming environment using natural processing model and fine-tuning and then generates and recommends the selectable blocks for the next step. To develop the model, the training dataset was produced by pre-processing 50 block codes that were on the popular block programming language web site 'Entry'. Also, after dividing the pre-processed blocks into training dataset, verification dataset and test dataset, we developed a model that generates block codes based on LSTM, Seq2Seq, and GPT-2 model. In the results of the performance evaluation of the developed model, GPT-2 showed a higher performance than the LSTM and Seq2Seq model in the BLEU and ROUGE scores which measure sentence similarity. The data results generated through the GPT-2 model, show that the performance was relatively similar in the BLEU and ROUGE scores except for the case where the number of blocks was 1 or 17.