• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.2
• /
• pp.102-110
• /
• 2017

Current word sense disambiguation techniques employ various machine learning-based methods. Various approaches have been proposed to address this problem, including the knowledge base approach. This approach defines the sense of an ambiguous word in accordance with knowledge base information with no training corpus. In unsupervised learning techniques that use a knowledge base approach, graph-based and similarity-based methods have been the main research areas. The graph-based method has the advantage of constructing a semantic graph that delineates all paths between different senses that an ambiguous word may have. However, unnecessary semantic paths may be introduced, thereby increasing the risk of errors. To solve this problem and construct a fine-grained graph, in this paper, we propose a model that iteratively constructs the graph while eliminating unnecessary nodes and edges, i.e., senses and semantic paths. The hybrid similarity estimation model was applied to estimate a more accurate sense in the constructed semantic graph. Because the proposed model uses BabelNet, a multilingual lexical knowledge base, the model is not limited to a specific language.

• Phonetics and Speech Sciences
• /
• v.1 no.2
• /
• pp.63-73
• /
• 2009

The present study was conducted to explore how the processing of lexical ambiguity between homonymy and polysemy differs from each other, and whether the representation of mental lexicon was separated from each lexical ambiguity by a semantic priming paradigm. Homonymy (M1 means the literal meaning of '사과', i.e. apple and M2 means another literal meaning of '사과', i.e. apologize) was used in Experiment I, and polysemy (M2 means the literal meaning of '바람', i.e. wind and M2 means the figurative meaning of '바람', i.e. wanton) was used in Experiment 2. The results of both experiments showed that a significant semantic priming effect occurs regardless of the type of ambiguities (homonymy and polysemy) and the difference of their semantic processes. However, the semantic priming effect for polysemy was larger than that for homonymy. This result supports the hypothesis that the semantic process of homonymy is different from that of polysemy.

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.81-92
• /
• 2003

Generalized LR parsing is one of the enhanced LR parsing methods so that it overcome the limit of one-way linear stack of the traditional LR parser using graph-structured stack, and it has been playing an important role of a firm starting point to generate other variations for NL parsing equipped with various mechanisms. In this paper, we propose a conditional Action Model that can solve the problems of conventional probabilistic GLR methods. Previous probabilistic GLR parsers have used relatively limited contextual information for disambiguation due to the high complexity of internal GLR stack. Our proposed model uses Surface Phrasal Types representing the structural characteristics of the parse for its additional contextual information, so that more specified structural preferences can be reflected into the parser. Experimental results show that our GLR parser with the proposed Conditional Action Model outperforms the previous methods by about 6-7% without any lexical information, and our model can utilize the rich stack information for syntactic disambiguation of probabilistic LR parser.

• Korean Journal of Cognitive Science
• /
• v.17 no.4
• /
• pp.303-321
• /
• 2006

According to Harris'(1966) distributional hypothesis, understanding the meaning of a word is thought to be dependent on its context. Under this hypothesis about human language ability, this paper proposes a computational model for native speaker's language processing mechanism concerning word sense disambiguation, based on two sets of experiments. Among the three computational models discussed in this paper, namely, the logic model, the probabilistic model, and the probabilistic inference model, the experiment shows that the logic model is first applied fer semantic disambiguation of the key word. Nexr, if the logic model fails to apply, then the probabilistic model becomes most relevant. The three models were also compared with the test results in terms of Pearson correlation coefficient value. It turns out that the logic model best explains the human decision behaviour on the ambiguous words, and the probabilistic inference model tomes next. The experiment consists of two pans; one involves 30 sentences extracted from 1 million graphic-word corpus, and the result shows the agreement rate anong native speakers is at 98% in terms of word sense disambiguation. The other pm of the experiment, which was designed to exclude the logic model effect, is composed of 50 cleft sentences.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.38 no.1
• /
• pp.49-63
• /
• 2010

This study was intended to analyze and interpret the pattern of naming the domestic apartment brand from a semiologic viewpoint in a bid to review the meaning and value of apartment brand, while on the other hand, evaluating the characteristics of persuasive message pursued by current apartment brand in 2010, and consequently, the conclusion of the study is outlined as follows. 1. As a result of analyzing the coinage of branding naming, the words such as combination, joint and blending pattern tended to dominate, which seemed to attempt to represent the variety of values of the housing culture. Brand ideation tends to stress the character symbolism and polysemic message using syllepsis, and the experimental attempt to revive the traditional dwelling concept in a modern sense in a way of combining the archaic word with the Chinese character was found as well. 2. As a result of analyzing the frequency of verbal identity and lexeme of domestic apartments, those frequently used are in order of ville, nature, beauty(美), park, hi, green, palace(宮), nobility and center(tra), which are the lexemes representing the landscape, view, nature and dignity. 3. As a result of identifying the pattern of lexeme using analysis frame based on existing researches such as apartment brand positioning, the most important external core concepts controlling the direction and value of apartment brand are 'environment-orientated' and 'emotion-orientated', and internally, 'function-oriented'. Given the persuasive language expressing the 'environment-oriented' feature and the priority of brand lexeme are garden, park, view and the nature, a landscape-oriented persuasive message is seen to be surging in brand naming. 4. An emotion-oriented persuasive language such as dignity axis having major lexeme represented by palace, nobility, class and a pride axis having major semantic elements represented by human, I and you are used as major value concepts and persuasive language that lead domestic apartment brands to differentiation and upgradation. 5. Among the lexemes focusing on view from environment-oriented standpoint, hi, hill, tower, view, mark, heights are the trend pursued by high-rise apartment aiming at the view such as residential-commercial apartment, and thus the persuasive language focusing on high-rise concept is expected to become the element dominating the trend of apartment brand for the time being.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.191-194
• /
• 2015

청각장애인을 위한 지상파방송 서비스 중 자막방송은 100%에 가까운 편성 비율을 달성하고 있지만, 수화방송은 방송화면을 가리는 특성과 비용 등의 문제로 5% 수준의 편성에 그치고 있다. 본 연구에서는 자막방송을 수화로 번역하여 그래픽 수화 방송을 생성함으로써 수화방송의 비율을 높이고자 한다. 일기예보에 한정하여 수화방송을 생성한 기존 연구 결과를 바탕으로 모든 방송 프로그램에 적용 가능한 그래픽 수화방송 시스템을 제안한다. 자막방송 문장을 형태소별로 분석한 다음 중요 품사 위주로 단어 단위로 번역하고, 한국어 어휘의미망을 이용하여 수화사전에 없는 단어를 대표어로 대체하였다. 형제어와 문맥 정보를 이용하여 중의성 단어를 성공적으로 번역하였다. 기존 일기예보 수화방송 시스템의 수화 사전과 수화 모션 데이터베이스를 추가 구축하였다. 자동번역 기술이 전문 수화 통역사의 수준을 따라잡을 수는 없지만 향후 수화방송도 선택적 서비스가 가능해지고 수화통역사의 수화방송이 모든 프로그램에 편성될 때까지 본 시스템이 보조적 시청 수단으로 사용 가능할 것이다.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.59-63
• /
• 2007

Neuromagnetic fields were recorded from normal 10 subjects to investigate the time course of cerebral neural activation during the resolution of lexical ambiguity. All recordings were made using a whole-head 306-channel MEG (Elekta Neuromag TM Inc., $Vectorview^{TM}$). The observed activity was described by sLORETA (standardized low resolution brain electromagnetic tomography) techniques implemented in CURRY software (Neuroscan). In the results, bilaterally occipito-temporal lobe was activated at 170ms. At 250ms was associated with bilateral temporal lobe during ambiguous condition, whereas in left parietal, temporal lobe on unambiguous condition. The left frontal lobe, temporal lobe were activated at 350ms for all condition. At approximately 430ms, was activated in right frontal, temporal lobe on the resolving ambiguous condition, in left parietal lobe, right temporal lobe on the preserving ambiguous condition. In conclusion, the cerebral activations related to the resolving lexical ambiguity were right frontal lobe and the areas of mountainous ambiguity were left parietal lobe.

• Phonetics and Speech Sciences
• /
• v.1 no.1
• /
• pp.87-91
• /
• 2009

The purpose of this study was to examine the characteristics of prosody of utterance of ambiguous sentences in patients with neurogenic communication disorders. Ambiguous words on which prosody may have an impact were used to investigate this matter. The characteristics of tone duration, pitch and intensity were analyzed to examine the characteristics of prosody in patients with lesions in the left or right hemisphere and normal controls. The whole process was recorded using a Praat 4.3.14 and for statistical analyses, two-way Anova and multiple comparative analyses were carried out using SPSS10.0 for Windows. The conclusions of this study are as follows: The length of vowel in homograph in Korean was different depending on the meaning and the duration of vowel was the longest in patients with lesions in the left hemisphere. There was agreed that they had problem of timing of prosody(Danly & Shapiro, 1982). On the other hand, there found that patients with lesions in the right hemisphere had deficiency of changeability in pitch. Among various acoustic parameters, this study focused on the duration which are closely related to suprasegmental characteristics of prosody. More acoustic parameters should be taken into account in future studies.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.75-77
• /
• 2021

A variety of search engines are currently in use. The search engine supports the retrieval of data required by users through three stages: crawling, index generation, and output of search results based on meta-tag information. However, a large number of documents obtained by searching for keywords are often unrelated or scarce. Because of these problems, it takes time and effort to grasp the content from the search results and classify the accuracy. The index of search engines is updated periodically, but the criteria for weighted values and update periods are different from one search engine to another. Therefore, this paper uses the LSTM model, which extracts the relationship between keywords entered by the user and documents instead of the existing search engine, and improves the relationship between keywords and documents by entering keywords that the user wants to find.

• Journal of Digital Contents Society
• /
• v.18 no.7
• /
• pp.1259-1265
• /
• 2017

While there is consensus on the educational potential of serious games, there is still a lack of methodology and tools to support analysis and evaluation as well as design. This paper intends to explore the new methodology or design direction by analyzing pedagogy-related research required for serious games. To do this, we analyzed 4DF(Four Dimensional Framework), GOM(Game Object Model), LM(Learning Mechanics)-GM(Game Mechanics) and a framework for teacher. One of the biggest issues faced by educational games is the inadequate integration of education and game principles. This is due to a variety of factors, including the fact that game designers and educational professionals do not share a common vocabulary or work domain perspective.