• Korean Journal of Cognitive Science
• /
• v.9 no.1
• /
• pp.13-29
• /
• 1998

This literature review explores the possibilities for the automatic processing to account for the people's responses to emotional stimuli. The most fundamental question is if some parts of emotions are experienced without any intrusion of cognitions. In other words. can emotions be processed completely implicitly$\ulcorner$ Some studies advocate emotion related processes are much more immediate and primary than semantic processes. The phenomena to catch up the emotive values of stimuli even subliminally suggest that the implicit knowledge structure takes charge of this automatic processes of emotional information. This study summarizes the explanatory scheme of emotional processing by means of applying implicit memory principle and physiological evidences related to e emotional memories.

• International Journal of Advanced Culture Technology
• /
• v.5 no.1
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.43-54
• /
• 2019

Currently, a majority of artificial intelligence is used to secure big data; however, it is concentrated in a few of major companies. Therefore, automatic data augmentation and efficient learning algorithms for small-scale data will become key elements in future artificial intelligence competitiveness. In addition, it is necessary to develop a technique to learn meanings, correlations, and time-related associations of complex modal knowledge similar to that in humans and expand and transfer semantic prediction/knowledge inference about unknown data. To this end, a neural memory model, which imitates how knowledge in the human brain is processed, needs to be developed to enable knowledge expansion through modality cooperative learning. Moreover, declarative and procedural knowledge in the memory model must also be self-developed through human interaction. In this paper, we reviewed this essential methodology and briefly described achievements that have been made so far.

• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.614-627
• /
• 2022

Aspect-based sentiment analysis is to discover the sentiment polarity towards an aspect from user-generated natural language. So far, most of the methods only use the implicit position information of the aspect in the context, instead of directly utilizing the position relationship between the aspect and the sentiment terms. In fact, neighboring words of the aspect terms should be given more attention than other words in the context. This paper studies the influence of different position embedding methods on the sentimental polarities of given aspects, and proposes a position embedding interactive attention network based on a long short-term memory network. Firstly, it uses the position information of the context simultaneously in the input layer and the attention layer. Secondly, it mines the importance of different context words for the aspect with the interactive attention mechanism. Finally, it generates a valid representation of the aspect and the context for sentiment classification. The model which has been posed was evaluated on the datasets of the Semantic Evaluation 2014. Compared with other baseline models, the accuracy of our model increases by about 2% on the restaurant dataset and 1% on the laptop dataset.

• Journal of the Korean Society for information Management
• /
• v.15 no.3
• /
• pp.133-150
• /
• 1998

For the purpose of new‘organizational knowledge centric knowledge management’, this paper proposes the knowledge creating organizational memory which shows the knowledge creation in organization according to the dialectical circulation between the domain knowledge and the task knowledge, based on the Yin Yang theory. This paper defines two kinds of organizational knowledge such as the domain knowledge and task knowledge and designs them in the pursuit of its lifecycle. Knowledge creating organizational memory is designed to three knowledge components that circulate through the domain knowledge and the task knowledge according to the object-oriented methodology. Organizational knowledge is designed into the graphical structure of ( i ) knowledge ( ⅱ ) relation between knowledge objects and ( ⅲ ) degree of relation, which receive the legacy of organizational knowledge such as data schema, process model and knowledge base. This design of organizational knowledge can be applied to CBR(Case Based Reasoning), one of knowledge mining tools to create new organizational knowledge.

• The Journal of the Korea Contents Association
• /
• v.15 no.4
• /
• pp.545-555
• /
• 2015

We investigated the influence of negative emotion such as state-trait anxiety and depression and working memory (WM) on Foreign Language Vocabulary Learning (FLVL) of South Korean university students. Also, its implications for developing contents for FLVL were discerned. To do so, state-trait anxiety and depression inventories as well as four kinds of WM test were performed for 132 undergraduate students. Participants also had two semantic learning sessions for Swahili words. The mean scores of negative emotions were normal level. The results of structural equation modeling (SEM) showed that there was no effect of negative emotion on FLVL, while direct effects of the negative emotion on WM and the WM on FLVL were significant. Such results suggested that FLVL would be weakened, with the result that WM had been impaired by negative emotions. These outcomes suggested that when developing FLVL content for university students, it is necessary to consider the negative emotions of foreign language learners and to develop the contents for FLVL in the light of WM load.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.1
• /
• pp.19-30
• /
• 2012

The context aware service is the service to provide useful information to the users by recognizing surroundings around people who receive the service via computer based on computing and communication, and by conducting self-decision. But CAS(Context Awareness System) shows the weak point of small-scale context awareness processing capacity due to restricted mobile function under the current mobile environment, memory space, and inference cost increment. In this paper, we propose a mobile cloud context system with using Google App Engine based on PaaS(Platform as a Service) in order to get context service in various mobile devices without any subordination to any specific platform. Inference design method of the proposed system makes use of knowledge-based framework with semantic inference that is presented by SWRL rule and OWL ontology and Jess with rule-based inference engine. As well as, it is intended to shorten the context service reasoning time with mapping the regular reasoning of SWRL to Jess reasoning engine by connecting the values such as Class, Property and Individual which are regular information in the form of SWRL to Jess reasoning engine via JessTab plug-in in order to overcome the demerit of queries reasoning method of SparQL in semantic search which is a previous reasoning method.

• Korean Journal of Cognitive Science
• /
• v.30 no.1
• /
• pp.31-50
• /
• 2019

The present study is designed to investigate the effect of perceptive, emotional and semantic distinctiveness on retrieval-induced forgetting(RIF). Experiment 1 was designed to construct a category and category list for RIF experimental paradigm and to investigate the effects of perceptual distinctness on retrieval-induced forgetting. It was used for the list consisting of the six categories and six words in each category list. In controlled conditions, all the stimuli were presented in black and Gothic. In contrast, perceptual distinctiveness conditions, half of the category list were presented in red and Gungseoche. RIF was observed in all conditions. Experiment 2 was designed to investigate the effects of semantic and emotional distinctiveness on retrieval-induced forgetting. In neutral conditions, adjectives related to items were added. In the emotional distinctiveness condition, half of the items in the category were manipulated in such a way as to add the negative adjectives. In the semantic distinctiveness condition, half of the items in the category were manipulated in such a way as to add the inappropriate adjective. As a result, RIF occurred in the neutral condition, but RIF did not occur in both the emotional discrimination condition and the semantic discrimination. These results suggest the possibility that the RIF will not occur when the distinctiveness occurs within a categorical relationship.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.192-200
• /
• 2012

In order for humans and robots to interact in daily life, robots need to understand human speech and link it to their actions. This paper proposes a hierarchical behavior model for robot action control using natural language commands. The model, which consists of episodes, primitive actions and atomic functions, uses a sentential cognitive system that includes multiple modules for perception, action, reasoning and memory. Human speech commands are translated to sentences with a natural language processor that are syntactically parsed. A semantic parsing procedure was applied to human speech by analyzing the verbs and phrases of the sentences and linking them to the cognitive information. The cognitive system performed according to the hierarchical behavior model, which consists of episodes, primitive actions and atomic functions, which are implemented in the system. In the experiments, a possible episode, "Water the pot," was tested and its feasibility was evaluated.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.159-162
• /
• 2017

Long Short-Term Memory Recurrent Neural Network(LSTM RNN)는 순차 데이터 모델링에 적합한 딥러닝 모델이다. Bidirectional LSTM RNN(BiLSTM RNN)은 RNN의 그래디언트 소멸 문제(vanishing gradient problem)를 해결한 LSTM RNN을 입력 데이터의 양 방향에 적용시킨 것으로 입력 열의 모든 정보를 볼 수 있는 장점이 있어 자연어처리를 비롯한 다양한 분야에서 많이 사용되고 있다. Highway Network는 비선형 변환을 거치지 않은 입력 정보를 히든레이어에서 직접 사용할 수 있게 LSTM 유닛에 게이트를 추가한 딥러닝 모델이다. 본 논문에서는 Highway Network를 한국어 의미역 결정에 적용하여 기존 연구 보다 더 높은 성능을 얻을 수 있음을 보인다.