• Journal of the Korea Society of Computer and Information
• /
• v.21 no.11
• /
• pp.85-91
• /
• 2016

This paper proposes a collective approach to cited text recognition by exploiting a set of citing text from different articles citing the same article. First, the proposed method gathers highly-ranked cited sentences from the cited article using a group of citing text to create a collective information of probable cited sentences. Then, such collective information is used to determine final cited sentences among highly-ranked sentences from similarity-based cited text recognition. Experiments have been conducted on the data set which consists of research articles from a computational linguistics domain. Evaluation results showed that the proposed method could improve the performance of similarity-based baseline approaches.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.288-298
• /
• 2021

Abstractive text summarization is a process of making a summary of a given text by paraphrasing the facts of the text while keeping the meaning intact. The manmade summary generation process is laborious and time-consuming. We present here a summary generation model that is based on multilayered attentional peephole convolutional long short-term memory (MAPCoL; LSTM) in order to extract abstractive summaries of large text in an automated manner. We added the concept of attention in a peephole convolutional LSTM to improve the overall quality of a summary by giving weights to important parts of the source text during training. We evaluated the performance with regard to semantic coherence of our MAPCoL model over a popular dataset named CNN/Daily Mail, and found that MAPCoL outperformed other traditional LSTM-based models. We found improvements in the performance of MAPCoL in different internal settings when compared to state-of-the-art models of abstractive text summarization.

• Smart Media Journal
• /
• v.5 no.3
• /
• pp.30-34
• /
• 2016

Nowadays, there are a lot of Korean documents, which often need to be identified in one of printed or handwritten text. Early methods for the identification use structural features, which can be simple and easy to apply to text of a specific font, but its performance depends on the font type and characteristics of the text. Recently, the bag-of-words model has been used for the identification, which can be invariant to changes in font size, distortions or modifications to the text. The method based on bag-of-words model includes three steps: word segmentation using connected component grouping, feature extraction, and finally classification using SVM(Support Vector Machine). In this paper, bag-of-words model based method is proposed using SURF(Speeded Up Robust Feature) for the identification of machine printed and handwritten text in Korean documents. The experiment shows that the proposed method outperforms methods based on structural features.

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.179-185
• /
• 2017

Document summarization aims to generate a summary that is consistent and contains the highly related sentences in a document. In this study, we implemented for document summarization that extracts highly related sentences from a whole document by considering both similarities and entailment relations between sentences. Accordingly, we proposed a new algorithm, TextRank-NLI, which combines a Recurrent Neural Network based Natural Language Inference model and a Graph-based ranking algorithm used in single document extraction-based summarization task. In order to evaluate the performance of the new algorithm, we conducted experiments using the same datasets as used in TextRank algorithm. The results indicated that TextRank-NLI showed 2.3% improvement in performance, as compared to TextRank.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.761-772
• /
• 2020

This paper presents an automatic proficiency assessment method for a non-native Korean read utterance using bidirectional long short-term memory (BLSTM)-based acoustic models (AMs) and speech data augmentation techniques. Specifically, the proposed method considers two scenarios, with and without prompted text. The proposed method with the prompted text performs (a) a speech feature extraction step, (b) a forced-alignment step using a native AM and non-native AM, and (c) a linear regression-based proficiency scoring step for the five proficiency scores. Meanwhile, the proposed method without the prompted text additionally performs Korean speech recognition and a subword un-segmentation for the missing text. The experimental results indicate that the proposed method with prompted text improves the performance for all scores when compared to a method employing conventional AMs. In addition, the proposed method without the prompted text has a fluency score performance comparable to that of the method with prompted text.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.4
• /
• pp.131-137
• /
• 2018

People write reviews of numerous products or services on the Internet, in their blogs or community bulletin boards. These unstructured data contain important emotions and opinions about the author's product or service, which can provide important information for future product design or marketing. However, this text-based information cannot be evaluated quantitatively, and thus they are difficult to apply to mathematical models or optimization problems for product design and improvement. Therefore, this study proposes a method to quantitatively extract user's opinion or preference about a specific product or service by utilizing a lot of text-based information existing on the Internet or online. The extracted unstructured text information is decomposed into basic unit words, and positive rate is evaluated by using existing emotional dictionaries and additional lists proposed in this study. This can be a way to effectively utilize unstructured text data, which is being generated and stored in vast quantities, in product or service design. Finally, to verify the effectiveness of the proposed method, a case study was conducted using movie review data retrieved from a portal website. By comparing the positive rates calculated by the proposed framework with user ratings for movies, a guideline on text mining based evaluation of unstructured data is provided.

• Asia pacific journal of information systems
• /
• v.12 no.4
• /
• pp.77-99
• /
• 2002

This study compares avatar-based chatting and text-based chatting. The comparison focuses on the effect of different chatting methods on user perception such as flow, social presence, and media richness. Especially the effects of avatar are examined across varying task types-work-oriented and fun-oriented. To accomplish this objective, a laboratory experiment was conducted using 80 experienced subjects. The results indicate that avatar-based chatting was more playfulness than text-based chatting in general. However, the effects of chatting methods on user perception were quite different according to the task types. There was no significant difference between avatar-based chatting and text-based chatting in the fun-oriented task, but avatar-based chatting was perceived as a more playful, focused, telepresent, and social present method in the work-oriented task.

• International Journal of Contents
• /
• v.14 no.4
• /
• pp.86-91
• /
• 2018

Text has evolved along with the history of art as a means of communicating human intentions and emotions. In addition, text visualization artworks have been combined with the social form and contents of new media to produce social messages and related meanings. Recently, in text visualization artworks combined with digital media, communication forms with viewers are changing instantly and interactively, and viewers are actively participating in creating artworks by direct engagement. Interactive text visualization with additional viewer's interaction, generates external dynamics from text shapes and internal dynamics from embedded meanings of text. The purpose of this study is to propose a visual dynamics model to express the dynamics of text and to implement a text visualization system based on the model. It uses the deconstruction of the imaged text to create an interactive text visualization system that reacts to the gestures of the viewer in real time. Visual Transformation synchronized with the intentions of the viewer prevent the text from remaining in the interpretation of language symbols and extend the various meanings of the text. The visualized text in various forms shows visual dynamics that interpret the meaning according to the cultural background of the viewer.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1535-1545
• /
• 2022

Sign language has completely different meaning depending on the direction of the hand or the change of facial expression even with the same gesture. In this respect, it is crucial to capture the spatial-temporal structure information of each movement. However, sign language translation studies based on Sign2Gloss2Text only convey comprehensive spatial-temporal information about the entire sign language movement. Consequently, detailed information (facial expression, gestures, and etc.) of each movement that is important for sign language translation is not emphasized. Accordingly, in this paper, we propose Spatial-temporal Keypoints Centered Sign2Gloss2Text Translation, named STKC-Sign2 Gloss2Text, to supplement the sequential and semantic information of keypoints which are the core of recognizing and translating sign language. STKC-Sign2Gloss2Text consists of two steps, Spatial Keypoints Embedding, which extracts 121 major keypoints from each image, and Temporal Keypoints Embedding, which emphasizes sequential information using Bi-GRU for extracted keypoints of sign language. The proposed model outperformed all Bilingual Evaluation Understudy(BLEU) scores in Development(DEV) and Testing(TEST) than Sign2Gloss2Text as the baseline, and in particular, it proved the effectiveness of the proposed methodology by achieving 23.19, an improvement of 1.87 based on TEST BLEU-4.

• Journal of the Ergonomics Society of Korea
• /
• v.26 no.2
• /
• pp.149-155
• /
• 2007

Recently, various devices requiring text input such as mobile phone IPTV, PDA and UMPC are emerging. The frequency of text entry for them is also increasing. This study was focused on the evaluation of Korean text entry interface. Various models to evaluate text entry interfaces have been proposed. Most of models were based on human cognitive process for text input. The cognitive process was divided into two components; visual scanning process and finger movement process. The time spent for visual scanning process was modeled as Hick-Hyman law, while the time for finger movement was determined as Fitts' law. There are three questions on the model-based evaluation of text entry interface. Firstly, are human cognitive processes (visual scanning and finger movement) during the entry of text sequentially occurring as the models. Secondly, is it possible to predict real text input time by previous models. Thirdly, does the human cognitive process for text input vary according to users' text entry speed. There was time gap between the real measured text input time and predicted time. The time gap was larger in the case of participants with high speed to enter text. The reason was found out investigating Eye-Hand Coordination during text input process. Differently from an assumption that visual scan on the keyboard is followed by a finger movement, the experienced group performed both visual scanning and finger movement simultaneously. Arrival Lead Time was investigated to measure the extent of time overlapping between two processes. 'Arrival Lead Time' is the interval between the eye fixation on the target button and the button click. In addition to the arrival lead time, it was revealed that the experienced group uses the less number of fixations during text entry than the novice group. This result will contribute to the improvement of evaluation model for text entry interface.