• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2009년도 추계학술발표대회
• /
• pp.239-240
• /
• 2009

We live in a flat world in which globalization fosters communication, travel, and trade among more than 150 countries and thousands of languages. To surmount the barriers among these languages, translation is required; Speech-to-Speech translation will automate the process. Thanks to recent advances in Automatic Speech Recognition (ASR), Machine Translation (MT), and Text-to-Speech (TTS), one can now utilize a system to translate a speech of source language to a speech of target language and vice versa in affordable manner. The three phase process establishes that the source speech be transcribed into a (set of) text of the source language (ASR) before the source text is translated into the target text (MT). Finally, the target speech is synthesized from the target text (TTS).

• 한국독어학회지:독어학
• /
• 제9집
• /
• pp.169-193
• /
• 2004

In simultaneous interpreting, if the syntactic structure of the source language and the target language are very different, interpreters have to wait before being able to reformulate the source text segments into a meaningful utterance in target language. It is inevitable to adapt the target language structure to that of the source language so as not to unduly increase the memory load and to minimize the pause. While such adaptation enables simultaneous interpretating, it results in damaging the perspective coherence of the text. Discovering when such perspective coherence is impaired, and how the problem can be relieved, will enable interpreters to enhance their performance. This paper analyses the reasons for perspective coherence damage by looking at some examples of German-Korean simultaneous interpreting.

• Journal of information and communication convergence engineering
• /
• 제18권1호
• /
• pp.33-38
• /
• 2020

Elasticsearch is an open source search and analytics engine that can search petabytes of data in near real time. It is designed as a distributed system horizontally scalable and highly available. It provides RESTful APIs, thereby making it programming-language agnostic. Full text search of multilingual text requires language-specific analyzers and field mappings appropriate for indexing and searching multilingual text. Additionally, a language detector can be used in conjunction with the analyzers to improve the multilingual text search. Elasticsearch provides more than 40 language analysis plugins that can process text and extract language-specific tokens and language detector plugins that can determine the language of the given text. This study investigates three different approaches to index and search Chinese, Japanese, and Korean (CJK) text (single analyzer, multi-fields, and language detector-based), and identifies the advantages of the language detector-based approach compared to the other two.

• Asian Journal for Public Opinion Research
• /
• 제9권1호
• /
• pp.25-47
• /
• 2021

This study analyzes 419 fake news items published in India, a fake-news-prone country, to identify the major themes, content types, and sources of social media fake news. The results show that fake news shared on social media has six major themes: health, religion, politics, crime, entertainment, and miscellaneous; eight types of content: text, photo, audio, and video, text & photo, text & video, photo & video, and text & photo & video; and two main sources: online sources and the mainstream media. Health-related fake news is more common only during a health crisis, whereas fake news related to religion and politics seems more prevalent, emerging from online media. Text & photo and text & video have three-fourths of the total share of fake news, and most of them are from online media: online media is the main source of fake news on social media as well. On the other hand, mainstream media mostly produces political fake news. This study, presenting some novel findings that may help researchers to understand and policymakers to control fake news on social media, invites more academic investigations of religious and political fake news in India. Two important limitations of this study are related to the data source and data collection period, which may have an impact on the results.

• ETRI Journal
• /
• 제43권2호
• /
• pp.288-298
• /
• 2021

Abstractive text summarization is a process of making a summary of a given text by paraphrasing the facts of the text while keeping the meaning intact. The manmade summary generation process is laborious and time-consuming. We present here a summary generation model that is based on multilayered attentional peephole convolutional long short-term memory (MAPCoL; LSTM) in order to extract abstractive summaries of large text in an automated manner. We added the concept of attention in a peephole convolutional LSTM to improve the overall quality of a summary by giving weights to important parts of the source text during training. We evaluated the performance with regard to semantic coherence of our MAPCoL model over a popular dataset named CNN/Daily Mail, and found that MAPCoL outperformed other traditional LSTM-based models. We found improvements in the performance of MAPCoL in different internal settings when compared to state-of-the-art models of abstractive text summarization.

• 대한물리의학회지
• /
• 제14권3호
• /
• pp.55-62
• /
• 2019

PURPOSE: Text-mining has been shown to be useful for understanding the clinical characteristics and patients' concerns regarding a specific disease. Low back pain (LBP) is the most common disease in modern society and has a wide variety of causes and symptoms. On the other hand, it is difficult to understand the clinical characteristics and the needs as well as demands of patients with LBP because of the various clinical characteristics. This study examined online texts on LBP to determine of text-mining can help better understand general characteristics of LBP and its specific elements. METHODS: Online data from www.spine-health.com were used for text-mining. Keyword frequency analysis was performed first on the complete text of postings (full-text analysis). Only the sentences containing the highest frequency word, pain, were selected. Next, texts including the sentences were used to re-analyze the keyword frequency (pain-text analysis). RESULTS: Keyword frequency analysis showed that pain is of utmost concern. Full-text analysis was dominated by structural, pathological, and therapeutic words, whereas pain-text analysis was related mainly to the location and quality of the pain. CONCLUSION: The present study indicated that text-mining for a specific element (keyword) of a particular disease could enhance the understanding of the specific aspect of the disease. This suggests that a consideration of the text source is required when interpreting the results. Clinically, the present results suggest that clinicians pay more attention to the pain a patient is experiencing, and provide information based on medical knowledge.

• 전자공학회논문지A
• /
• 제33A권7호
• /
• pp.23-33
• /
• 1996

This paper deals with the design of a recursively-indexed binary code for facsimile soruces and its performance. Sources used here are run-lengths of white pixels form higher-resolution facsimile. The modified huffman code used for G.3 facsimile is chosen for the performance comparison. Experiments confirm the fact that recursive indexing preserves the entropy of a memoryless geometric source: the entropy of recursively-indexed physical surce iwth roughly geometric distributin remains within 2% of the empirical source entropy. The designed recursively-indexed binary codes consist of a code applied to text-type documents and to graphics - type documents is compared iwth that of the modified huffman code. Numerical resutls show that the modified huffman code performs well for text-type documents and not equally well for graphics-tyep documents. On the other hand, recursively-indexed binary codes have shown a better performance for graphics-type documents whose distribution are similar to a geometric distribution. Specifically, the code rates of recursively-indexed binary codes with 60 codewords are from 8% to 20% of the empirical source entropy smaller than that of th emodified huffman code with 91 codewords.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권9호
• /
• pp.4814-4832
• /
• 2019

Plagiarism detection is increasingly exploiting text alignment. Text alignment involves extracting the plagiarism passages in a pair of the suspicious document and its source document. The heuristics have achieved excellent performance in text alignment. However, the further improvements of the heuristic methods mainly depends more on the experiences of experts, which makes the heuristics lack of the abilities for continuous improvements. To address this problem, machine learning maybe a proper way. Considering the position relations and the context of text segments pairs, we formalize the text alignment task as a problem of sequence labeling, improving the current methods at the model level. Especially, this paper proposes to use the probabilistic graphical model to tag the observed sequence of pairs of text segments. Hence we present the sequence labeling approach for text alignment in plagiarism detection based on Conditional Random Fields. The proposed approach is evaluated on the PAN@CLEF 2012 artificial high obfuscation plagiarism corpus and the simulated paraphrase plagiarism corpus, and compared with the methods achieved the best performance in PAN@CLEF 2012, 2013 and 2014. Experimental results demonstrate that the proposed approach significantly outperforms the state of the art methods.

• 정보관리학회지
• /
• 제24권4호
• /
• pp.305-321
• /
• 2007

이 연구는 색인가가 주제 색인하는 과정에서 참조하는 여러 문서구성요소를 문서 범주화의 정보원으로 인식하여 이들이 문서 범주화 성능에 미치는 영향을 살펴보는데 그 목적이 있다. 이는 기존의 문서 범주화 연구가 전문(full text)에 치중하는 것과는 달리 문서구성요소로서 정보원의 영향을 평가하여 문서 범주화에 효율적으로 사용될 수 있는지를 파악하고자 한다. 전형적인 과학기술분야의 저널 및 회의록 논문을 데이터 집합으로 하였을때 정보원은 본문정보 중심과 문서구성요소중심으로 나뉘어 질 수 있다. 본문정보중심은 본론자체와 서론과 결론으로 구성되며, 문서구성요소중심은 제목, 인용, 출처, 초록, 키워드로 파악된다. 실험결과를 살펴보면, 인용, 출처, 제목정보원은 본문정보원과 비교하여 유의한 차이를 보이지 않으며, 키워드정보원은 본문 정보원과 비교하여 유의한 차이를 보인다. 이러한 결과는 색인가가 참고하는 문서구성요소로서의 정보원이 문서 범주화에 본문을 대신하여 효율적으로 활용될 수 있음을 보여주고 있다.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.1-6
• /
• 2023

Text mining (TM) is most widely used to process the various unstructured text documents and process the data present in the various domains. The other name for text mining is text classification. This domain is most popular in many domains such as movie reviews, product reviews on various E-commerce websites, sentiment analysis, topic modeling and cyber bullying on social media messages. Cyber-bullying is the type of abusing someone with the insulting language. Personal abusing, sexual harassment, other types of abusing come under cyber-bullying. Several existing systems are developed to detect the bullying words based on their situation in the social networking sites (SNS). SNS becomes platform for bully someone. In this paper, An Enhanced text mining approach is developed by using Ensemble Algorithm (ETMA) to solve several problems in traditional algorithms and improve the accuracy, processing time and quality of the result. ETMA is the algorithm used to analyze the bullying text within the social networking sites (SNS) such as facebook, twitter etc. The ETMA is applied on synthetic dataset collected from various data a source which consists of 5k messages belongs to bullying and non-bullying. The performance is analyzed by showing Precision, Recall, F1-Score and Accuracy.