• Journal of the Korean Society for information Management
• /
• v.34 no.4
• /
• pp.81-99
• /
• 2017

Technical documents are important research outputs generated by knowledge and information society. In order to properly use the technical documents properly, it is necessary to utilize advanced information processing techniques, such as summarization and information extraction. In this paper, to extract core information, we automatically extracted the terminologies and their definition based on definitional sentences patterns and the structure of technical documents. Based on this, we proposed the system to build a specialized terminology dictionary. And further we suggested the personalized services so that users can utilize the terminology dictionary in various ways as an knowledge memory. The results of this study will allow users to find up-to-date information faster and easier. In addition, providing a personalized terminology dictionary to users can maximize the value, usability, and retrieval efficiency of the dictionary.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.99-120
• /
• 2017

In order to develop a semiautomatic support system that allows researchers concerned to efficiently analyze the technical trends for the ever-growing industry and market. This paper introduces a couple of Korean sentence generation models that can automatically generate definitional statements as well as descriptions of technical terms and concepts. The proposed models are based on a deep learning model called LSTM (Long Sort-Term Memory) capable of effectively labeling textual sequences by taking into account the contextual relations of each item in the sequences. Our models take technical terms as inputs and can generate a broad range of heterogeneous textual descriptions that explain the concept of the terms. In the experiments using large-scale training collections, we confirmed that more accurate and reasonable sentences can be generated by CHAR-CNN-LSTM model that is a word-based LSTM exploiting character embeddings based on convolutional neural networks (CNN). The results of this study can be a force for developing an extension model that can generate a set of sentences covering the same subjects, and furthermore, we can implement an artificial intelligence model that automatically creates technical literature.