• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• Journal of the Korea Institute of Building Construction
• /
• v.12 no.2
• /
• pp.243-256
• /
• 2012

This study is the experimental study to improve the insulation of the fastening unit system, which has the most vulnerable insulation in the curtain walls. The Fastening Units were designed and fabricated to minimize the connection part of mullions. In addition, slight movements were taken into account and the performance of the middle layer was evaluated by forming an insulation layer with the vibration-proof rubber and the silicon to satisfy the mechanical and thermal performance criteria. A total of 10 experiments were performed under various conditions, such as indoor-outdoor temperature difference, type of insulation material, thickness of insulation material, and others. using the fabricated Fastening Units. As a result, the vibration-proof rubber insulation showed the temperature difference of $2.2^{\circ}C-5.0^{\circ}C$, and the silicon insulation showed the temperature difference of $2.8^{\circ}C-4.5^{\circ}C$, compared to the non-insulated Fasteniirature difference, typesng Units. When these results were compared with the psychometric chart graph, the insulated Fastening Unit designed in this study can be considered to prevent the dew condensation.

• MALSORI
• /
• no.21_24
• /
• pp.90-110
• /
• 1992

The purpose of this thesis is to investigate the intonation features of the last two syllables of rhythmic units, with the exception of the sentence final unit, in the Seoul dialect of Korean. The Model 5500 Sona-graph was used to measure the pitch and duration of the target syllables. There are two classes of materials. One class was designed to determine the intonation of rhythmic units in a natural situation and the other to investigate the intonation of rhythmic units in an artificial situation, in which speakers were asked to read the materials pausing only at the marked boundaries, with a view to identifying the intonation of Seoul dialect more clearly. The findings of this investigation are as follows: (1) Korean averages an 11% rising intonation between the two syllables at the end of a rhythmic unit. (2) The rising rate between the final two syllables' pitch values at the subject rhythmic unit is generally higher than those at other units in a sentence and it seems to be meaningful syntactically. (3) Before a boundary the rhythmic units undergo 'pre-lowering', in which the pitch gradually lowers from the first syllable to the penultimate. (4) Every syllable in each rhythmic unit tends to lengthen when speakers read the materials with a pause between units and the tendency is most salient at the final syllable before a boundary.

• Journal of applied mathematics & informatics
• /
• v.29 no.5_6
• /
• pp.1075-1080
• /
• 2011

Among the numerous topological indices considered in chemical graph theory, only a few have been found noteworthy in practical application, Randi$\acute{c}$ index is one of them. The dendrimer nanostars is a synthesized molecule built up from branched unit called monomers. In this article, we compute the Randi$\acute{c}$ index of two types of polymer dendrimers and a fullerene dendrimer.

• Bulletin of the Korean Mathematical Society
• /
• v.38 no.2
• /
• pp.285-292
• /
• 2001

The authors compute the Ricci curvature of the GRW space-time to obtain two conditions for the conjugate points which appear as the Timelike Convergence Condition(TCG) and the Jacobi inequality. Moreover, under such two conditions, we obtain a lower bound of the length of a unit timelike geodesic for focal points emanating form the immersed spacelike hypersurface, the graph over the fiber in the GRW space-time.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1983.10a
• /
• pp.112-117
• /
• 1983

In this paper, a functional m-redundant system, which is me-fault tolerant, is defined based on the graph-theory. This system is designed to be t fault-diagnosable by comparing its unit's outcomes without additive test functions, and so, the system down for diagnosis is not needed. the diagnostic model for this system is presented and this effectively uses system's redundancy. It is shown that this model can be converted into Preparata's model. Thus, the diagnostic characteristics of a functional m-redundant system is analyzed by the methods originated by Preparata et al..

• Journal of Korean Society on Water Environment
• /
• v.28 no.4
• /
• pp.574-581
• /
• 2012

It is important to analyze the status of water quality with relation to the stream flow to attain water quality goal more effectively in the unit watersheds for the management of Total Maximum Daily Loads (TMDLs). This study developed a flow duration-water quality distribution graph to figure out water quality appearances on the flow variation and analyzed contributions of water quality observations to the impaired water bodies quantitatively by hydrologic conditions. Factors relating to water quality variation can be analyzed more precisely and assessed on the base of quantified contributions. It is considered that this approach could be utilized to establish a more effective plan for the water quality improvement including the prioritization of pollution reduction options.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.87-92
• /
• 1998

In general, the synthesis unit database was constructed by recording isolated word. In that case, each boundary of word has typical prosodic pattern like a falling intonation or preboundary lengthening. To get natural synthetic speech using these kinds of database, we must artificially distort original speech. However, that artificial process rather resulted in unnatural, unintelligible synthetic speech due to the excessive prosodic modification on speech signal. To overcome these problems, we gathered thousands of sentences for synthesis database. To make a phone level synthesis unit, we trained speech recognizer with the recorded speech, and then segmented phone boundaries automatically. In addition, we used laryngo graph for the epoch detection. From the automatically generated synthesis database, we chose the best phone and directly concatenated it without any prosody processing. To select the best phone among multiple phone candidates, we used prosodic information such as break strength of word boundaries, phonetic contexts, cepstrum, pitch, energy, and phone duration. From the pilot test, we obtained some positive results.

• Journal of Korea Game Society
• /
• v.11 no.2
• /
• pp.3-11
• /
• 2011

A game designer is the initial design of the quest based on narrative. It is important that to predict game character of play experience to establish these static content. This paper deal with player's affective interaction distinguishing among game characters are perform quest-play based on their characteristic status. To achieve this, First of all, previous studies regarding pre-visualization of narrative structure for other visual media are reviewed. Secondly, it is specified that quest-play experience and player's cognitive behavior. At last, these features of status by character were pre-visualized with QUG(Quest Unit Graph), which could be represented differences in precess of quest-play through analysis on world of warcarft game. Previous research is about of numerical balance in terms of character's achievement, whereas this study is meaningful that is proposed that visual model of quest-play interaction focused on narrative structure to predict game designer's architecture of quest experience.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.6-10
• /
• 2023

High-potential data can be predicted and stored in the cache to prevent cache misses, thus reducing the processor's request and wait times. As a result, the processor can work non-stop, hiding memory latency. By utilizing the temporal/spatial locality of memory access, the prefetcher introduced to improve the performance of these computers predicts the following memory address will be accessed. We propose a prefetcher that applies the GRU model, which is advantageous for handling time series data. Display the currently accessed address in binary and use it as training data to train the Gated Recurrent Unit model based on the difference (delta) between consecutive memory accesses. Finally, using a GRU model with learned memory access patterns, the proposed data prefetcher predicts the memory address to be accessed next. We have compared the model with the multi-layer perceptron, but our prefetcher showed better results than the Multi-Layer Perceptron.