• (The) Research of the performance art and culture
• /
• no.42
• /
• pp.257-290
• /
• 2021

The Wonju Nongyo (agricultural work song) is geographically classified as eastern minyo (folk song) which has many distinctive, regional features such as tunes, forms and the use of a melodic line. There has been growing attention to the transmission value of the nongyo including the Wonju Eorirang of the Wonju Origol Nongyo and its region of origin. The Wonju Nongyo is of great value and worthy of preservation in the western part of Gangwon Province. For this reason, it seems fairer to say that a focus should be directed towards establishing the identity of the song and increasing the contextualisation of transmission. At the same time, the preservation association's efforts in passing the traditional song down and education activities fairly deserve equal attention. In addition to the way the folk songs are handed down, a discussion on the facilitation of their use will be required. An in-depth discussion about the restoration and use of the song will be encouraged in a multifaceted manner. Unfortunately, few of the previous literatures on nongyo has gone so far as to investigate Arirang as a separate research topic. In fact, the Wonju Origol Nongyo should be viewed as an intangible cultural asset that paved the way for performance artistry of the Korean agricultural work songs to be seen at a national folk art festival. From the perspective of regional characteristics (traditionally termed "tori"), the Wonju Eorirang represents the cultural value of the manners and customs of our locals which constitute unwritten and neglected literary property and musicality of the song. Particularly, a more attention should be paid to making a record of woodcutters and diversity of farmers' small cooperative groups. The existence of the Wonju Eorirang indicates that the melodies to which the song are sung in Nongyo are of infinite variety. A minyo-singer unfolds various journeys of life through various modes and structure of epic chants, ranging from first encounter, love to marriage, realistic problems to relationship with husband's family and death. The epic chant of the Wonju Origol Nongyo contains a rich variety of regional sentiments about life. In particular, the epic chants of the Galtteukgisor and Ssoeltteukgisori are a genius example of sexual satire and a sense of humor. In the past, the agricultural work songs were rhythmic songs served to synchronize physical movements in groups, coordinating tasks in upland farming and rice paddy with the usage of catchy, repetitive verses easy to pass down. The Wonju Origol Nongyo is a precursor of the work songs which took the farming activities a notch higher to be part of the excitement and festivals. In the context of transmission, a festival serves to demonstrate the value of history and life. The value of the Wonju Eorirang should be appreciated and a concerted effort should be made to find a way to facilitate the transmission of the folk song. A folk-singer is a traditional oral poet and a storyteller of minyo and the forms and species of melody solely depend on the signer. The combination of performance and witticism is shown by the singer freely expressing himself. The Origol Nongyo symbolizes ethnic arts cleverly combining playful effects such as tune, rhythm and old agricultural work of the region. It is to be hoped that much of the efforts is directed to designating such folk songs as the archetype of a cultural heritage. In terms of the foundation on which the folk songs are transmitted, the usage(Performance Content) of a community would be an alternative.

• 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.