• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2006년도 가을 학술발표논문집 Vol.33 No.2 (B)
• /
• pp.233-237
• /
• 2006

This study proposes an innovative measure for evaluating the performance of text clustering. In using K-means algorithm and Kohonen Networks for text clustering, the number clusters is fixed initially by configuring it as their parameter, while in using single pass algorithm for text clustering, the number of clusters is not predictable. Using labeled documents, the result of text clustering using K-means algorithm or Kohonen Network is able to be evaluated by setting the number of clusters as the number of the given target categories, mapping each cluster to a target category, and using the evaluation measures of text. But in using single pass algorithm, if the number of clusters is different from the number of target categories, such measures are useless for evaluating the result of text clustering. This study proposes an evaluation measure of text clustering based on intra-cluster similarity and inter-cluster similarity, what is called CI (Clustering Index) in this article.

• 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.

• 정보처리학회논문지B
• /
• 제16B권1호
• /
• pp.79-84
• /
• 2009

이 논문은 한국어 문장을 대상으로 구문요소의 전치를 기반으로 한 문서 워터마킹 방법을 제안한다. 한국어와 같은 교착어는 구문요소의 순서가 자유롭기 때문에 구문 트리 기반의 자연어 워터마킹을 위한 좋은 환경을 제공한다. 본 논문에서 제안하는 자연어 워터마킹 방법은 7단계로 구성되어 있다. 첫째, 문장의 구문분석을 수행한다. 다음으로, 구문요소가 해당 절의 범위 안에서만 전치되도록 범위를 한정하기 위하여 구문 트리로부터 각 절을 분할한다. 세 번째로, 전치를 위한 목표 구문요소를 선택한다. 네 번째, 목표 구문요소의 전치 후에도 문장의 의미나 문체의 변화가 최소화되도록 가장 자연스러운 전이위치를 결정한다. 그 후, 목표 구문요소에 대한 워터마크 비트를 삽입한다. 여섯 번째 단계로, 워터마크 비트가 목표 구문요소의 전치 방향과 상응하지 않으면 구문 트리에서 목표 구문요소를 전치한다. 마지막으로 변환된 구문 트리에서 워터마킹된 문서를 얻는다. 실험 결과를 통해 본 논문에서 제안한 방법의 적용률은 91.53%이고, 최종 워터마킹된 문장들 중 부자연스러운 문장의 비율은 23.16%로서 기존 시스템들보다 좋은 결과를 보여준다. 또한 워터마킹된 문장이 원시 문장과 같은 문체를 유지하고, 의미적인 왜곡없이 같은 정보를 나타내고 있다.

• 인지과학
• /
• 제34권4호
• /
• pp.259-275
• /
• 2023

본 연구는 McConkie와 Rayner(1975)가 고안한 움직이는 창 기법을 사용해 덩이글의 내용 난이도에 따른 글꼴 변화맹의 발생 여부를 조사했다. 이를 위해 움직이는 창이 처치된 읽기 과제 수행 중 본문 글꼴과 다른 표적 어절을 제시하고 참가자의 시선이 해당 어절 위치에 도착한 순간 표적 어절의 글꼴을 본문과 동일한 글꼴로 변화시켰다. 변화 이전 표적 어절의 글꼴은 본문 글꼴이 세리프인 경우 산세리프 글꼴이었으며 혹은 반대로 산세리프인 경우 세리프 글꼴이었다. 읽기 과제 종료 후 참가자의 절반 이상(62.5%)이 글꼴 변화를 탐지하지 못했다고 보고했다. 각 문장 내에서의 안구 운동을 관찰한 결과 덩이글 내용에 대한 이해가 어려웠을 때 안구운동 회귀횟수와 응시시간이 증가했고 도약거리가 단축되었다. 특히 회귀횟수 증가는 본문 글꼴이 세리프였을 때 즉 표적 어절 글꼴이 산세리프에서 세리프로 변화한 경우에만 분명했다. 이러한 결과는 내용 이해와 무관한 감각적 간섭은 읽기 수행 도중 잘 탐지되지 않지만, 과제 본문에 대한 내용 이해가 어려워지면 오히려 탐지될 가능성이 증가함을 시사한다. 더 나아가 이러한 예외적인 탐지의 가능성은 본문 덩이글 글꼴이 산세리프 글꼴인 경우보다 세리프 글꼴일 때 더 높아질 수 있음을 시사한다.

• International Journal of Computer Science & Network Security
• /
• 제22권8호
• /
• pp.242-248
• /
• 2022

The article presents the analysis of modern methods of automatic comparison of original and unoriginal text to detect textual plagiarism. The study covers two types of plagiarism - literal, when plagiarists directly make exact copying of the text without changing anything, and intelligent, using more sophisticated techniques, which are harder to detect due to the text manipulation, like words and signs replacement. Standard techniques related to extrinsic detection are string-based, vector space and semantic-based. The first, most common and most successful target models for detecting literal plagiarism - N-gram and Vector Space are analyzed, and their advantages and disadvantages are evaluated. The most effective target models that allow detecting intelligent plagiarism, particularly identifying paraphrases by measuring the semantic similarity of short components of the text, are investigated. Models using neural network architecture and based on natural language sentence matching approaches such as Densely Interactive Inference Network (DIIN), Bilateral Multi-Perspective Matching (BiMPM) and Bidirectional Encoder Representations from Transformers (BERT) and its family of models are considered. The progress in improving plagiarism detection systems, techniques and related models is summarized. Relevant and urgent problems that remain unresolved in detecting intelligent plagiarism - effective recognition of unoriginal ideas and qualitatively paraphrased text - are outlined.

• 영어어문교육
• /
• 제10권3호
• /
• pp.21-40
• /
• 2004

This study Questioned what happens in L2 reading comprehension of the expository text, as measured by recall and inference-making abilities, when a L2 reader was induced to develop a content schema about the topic of a target text, but the structure of that schema departs from the structure of the target text Seventy-four. Korean university students read either the same version text twice (consistent condition) or two different version texts (inconsistent condition) with a three-day interval between the two readings. The results of a verification test indicate that, for those subjects with higher L2 reading proficiency, the inconsistent condition was more beneficial than the consistent condition for the inference-making task. On the other hand, for lower-level L2 readers, the consistent condition was more favorable for the recall task. It was concluded that inducing a structurally inconsistent schema through an L2 pre-reading would be beneficial only when the reader's L2 linguistic ability is proficient enough to produce necessary propositions from the pre-reading.

• 한국컴퓨터정보학회논문지
• /
• 제24권7호
• /
• pp.31-37
• /
• 2019

Citation-based article summarization is to create a shortened text for an academic article, reflecting the content of citing sentences which contain other's thoughts about the target article to be summarized. To deal with the problem, this study introduces an extractive summarization method based on calculating a linear combination of various sentence salience scores, which represent the degrees to which a candidate sentence reflects the content of author's abstract text, reader's citing text, and the target article to be summarized. In the current study, salience scores are obtained by computing surface-level textual similarities. Experiments using CL-SciSumm datasets show that the proposed method parallels or outperforms the previous approaches in ROUGE evaluations against SciSumm-2017 human summaries and SciSumm-2016/2017 community summaries.

• ETRI Journal
• /
• 제36권5호
• /
• pp.704-713
• /
• 2014

Most natural language processing tasks depend on the outputs of some other tasks. Thus, they involve other tasks as subtasks. The main problem of this type of pipelined model is that the optimality of the subtasks that are trained with their own data is not guaranteed in the final target task, since the subtasks are not optimized with respect to the target task. As a solution to this problem, this paper proposes a consolidation of subtasks for a target task ($CST^2$). In $CST^2$, all parameters of a target task and its subtasks are optimized to fulfill the objective of the target task. $CST^2$ finds such optimized parameters through a backpropagation algorithm. In experiments in which text chunking is a target task and part-of-speech tagging is its subtask, $CST^2$ outperforms a traditional pipelined text chunker. The experimental results prove the effectiveness of optimizing subtasks with respect to the target task.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2003년도 제2차 연례학술대회 발표논문집
• /
• pp.86-94
• /
• 2003

Electronically available biological literature has been accumulated exponentially in the course of time. So, researches on automatically acquiring knowledge from these tremendous data by text mining technology become more and more prosperous. However, most of the previous researches are technology oriented and are not well focused in practical extraction target, hence result in low performance and inconvenience for the bio-researchers to actually use. In this paper, we propose a more biology oriented target domain specific text mining system, that is, POSTECH bio-text mining system (POSBIOTM), for signal transduction pathway extraction, especially for G protein-coupled receptor (GPCR) pathway. To reflect more domain knowledge, we specify the concrete target for pathway extraction and define the minimal pathway domain ontology. Under this conceptual model, POSBIOTM extracts interactions and entities of pathways from the full biological articles using a machine learning oriented extraction method and visualizes the pathways using JDesigner module provided in the system biology workbench (SBW) [14]