• ETRI Journal
• /
• v.44 no.5
• /
• pp.794-804
• /
• 2022

Transformer models have had a great impact on natural language processing (NLP) in recent years by realizing outstanding and efficient contextualized language models. Recent studies have used transformer-based language models for various NLP tasks, including Persian named entity recognition (NER). However, in complex tasks, for example, NER, it is difficult to determine which contextualized embedding will produce the best representation for the tasks. Considering the lack of comparative studies to investigate the use of different contextualized pretrained models with sequence modeling classifiers, we conducted a comparative study about using different classifiers and embedding models. In this paper, we use different transformer-based language models tuned with different classifiers, and we evaluate these models on the Persian NER task. We perform a comparative analysis to assess the impact of text representation and text classification methods on Persian NER performance. We train and evaluate the models on three different Persian NER datasets, that is, MoNa, Peyma, and Arman. Experimental results demonstrate that XLM-R with a linear layer and conditional random field (CRF) layer exhibited the best performance. This model achieved phrase-based F-measures of 70.04, 86.37, and 79.25 and word-based F scores of 78, 84.02, and 89.73 on the MoNa, Peyma, and Arman datasets, respectively. These results represent state-of-the-art performance on the Persian NER task.

• International Journal of Contents
• /
• v.17 no.4
• /
• pp.1-15
• /
• 2021

Named entity recognition (NER) is a crucial task for NLP, which aims to extract information from texts. To build NER systems, deep learning (DL) models are learned with dictionary features by mapping each word in the dataset to dictionary features and generating a unique index. However, this technique might generate noisy labels, which pose significant challenges for the NER task. In this paper, we proposed DL-dictionary features, and evaluated them on two datasets, including the OntoNotes 5.0 dataset and our new infectious disease outbreak dataset named GFID. We used (1) a Bidirectional Long Short-Term Memory (BiLSTM) character and (2) pre-trained embedding to concatenate with (3) our proposed features, named the Convolutional Neural Network (CNN), BiLSTM, and self-attention dictionaries, respectively. The combined features (1-3) were fed through BiLSTM - Conditional Random Field (CRF) to predict named entity classes as outputs. We compared these outputs with other predictions of the BiLSTM character, pre-trained embedding, and dictionary features from previous research, which used the exact matching and partial matching dictionary technique. The findings showed that the model employing our dictionary features outperformed other models that used existing dictionary features. We also computed the F1 score with the GFID dataset to apply this technique to extract medical or healthcare information.

• Journal of Technology Innovation
• /
• v.26 no.4
• /
• pp.199-232
• /
• 2018

There are increasing needs for understanding and fathoming of business management environment through big data analysis at industrial and corporative level. The research using the company disclosure information, which is comprehensively covering the business performance and the future plan of the company, is getting attention. However, there is limited research on developing applicable analytical models leveraging such corporate disclosure data due to its unstructured nature. This study proposes a text-mining-based analytical model for industrial and firm level analyses using publicly available company disclousre data. Specifically, we apply LDA topic model and word2vec word embedding model on the U.S. SEC data from the publicly listed firms and analyze the trends of business topics at the industrial and corporate levels. Using LDA topic modeling based on SEC EDGAR 10-K document, whole industrial management topics are figured out. For comparison of different pattern of industries' topic trend, software and hardware industries are compared in recent 20 years. Also, the changes of management subject at firm level are observed with comparison of two companies in software industry. The changes of topic trends provides lens for identifying decreasing and growing management subjects at industrial and firm level. Mapping companies and products(or services) based on dimension reduction after using word2vec word embedding model and principal component analysis of 10-K document at firm level in software industry, companies and products(services) that have similar management subjects are identified and also their changes in decades. For suggesting methodology to develop analysis model based on public management data at industrial and corporate level, there may be contributions in terms of making ground of practical methodology to identifying changes of managements subjects. However, there are required further researches to provide microscopic analytical model with regard to relation of technology management strategy between management performance in case of related to various pattern of management topics as of frequent changes of management subject or their momentum. Also more studies are needed for developing competitive context analysis model with product(service)-portfolios between firms.

• Journal of Information Technology Services
• /
• v.19 no.6
• /
• pp.1-13
• /
• 2020

Recently, 80% of big data consists of unstructured text data. In particular, various types of documents are stored in the form of large-scale unstructured documents through social network services (SNS), blogs, news, etc., and the importance of unstructured data is highlighted. As the possibility of using unstructured data increases, various analysis techniques such as text mining have recently appeared. Therefore, in this study, topic modeling technique was applied to the Korea Highway Corporation's voice of customer (VOC) data that includes customer opinions and complaints. Currently, VOC data is divided into the business areas of Korea Expressway Corporation. However, the classified categories are often not accurate, and the ambiguous ones are classified as "other". Therefore, in order to use VOC data for efficient service improvement and the like, a more systematic and efficient classification method of VOC data is required. To this end, this study proposed two approaches, including method using only the latent dirichlet allocation (LDA), the most representative topic modeling technique, and a new method combining the LDA and the word embedding technique, Word2vec. As a result, it was confirmed that the categories of VOC data are relatively well classified when using the new method. Through these results, it is judged that it will be possible to derive the implications of the Korea Expressway Corporation and utilize it for service improvement.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.11
• /
• pp.441-448
• /
• 2019

Previous researches on automatic spacing of Korean sentences has been researched to correct spacing errors by using n-gram based statistical techniques or morpheme analyzer to insert blanks in the word boundary. In this paper, we propose an end-to-end automatic word spacing by using deep neural network. Automatic word spacing problem could be defined as a tag classification problem in unit of syllable other than word. For contextual representation between syllables, Bi-LSTM encodes the dependency relationship between syllables into a fixed-length vector of continuous vector space using forward and backward LSTM cell. In order to conduct automatic word spacing of Korean sentences, after a fixed-length contextual vector by Bi-LSTM is classified into auto-spacing tag(B or I), the blank is inserted in the front of B tag. For tag classification method, we compose three types of classification neural networks. One is feedforward neural network, another is neural network language model and the other is linear-chain CRF. To compare our models, we measure the performance of automatic word spacing depending on the three of classification networks. linear-chain CRF of them used as classification neural network shows better performance than other models. We used KCC150 corpus as a training and testing data.

• Journal of the Korean Society of Physical Medicine
• /
• v.16 no.2
• /
• pp.91-100
• /
• 2021

PURPOSE: This study analyzed the trends and characteristics of shoulder rehabilitation research through keyword analysis, and their relationships were modeled using text mining techniques. METHODS: Abstract data of 10,121 articles in which abstracts were registered on the MEDLINE of PubMed with 'shoulder' and 'rehabilitation' as keywords were collected using python. By analyzing the frequency of words, 10 keywords were selected in the order of the highest frequency. Word-embedding was performed using the word2vec technique to analyze the similarity of words. In addition, the groups were classified and analyzed based on the distance (cosine similarity) through the t-SNE technique. RESULTS: The number of studies related to shoulder rehabilitation is increasing year after year, keywords most frequently used in relation to shoulder rehabilitation studies are 'patient', 'pain', and 'treatment'. The word2vec results showed that the words were highly correlated with 12 keywords from studies related to shoulder rehabilitation. Furthermore, through t-SNE, the keywords of the studies were divided into 5 groups. CONCLUSION: This study was the first study to model the keywords and their relationships that make up the abstracts of research in the MEDLINE of Pub Med related to 'shoulder' and 'rehabilitation' using text-mining techniques. The results of this study will help increase the diversifying research topics of shoulder rehabilitation studies to be conducted in the future.

• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.149-160
• /
• 2017

Sentiment analysis is the process of determining whether a piece of document, text or conversation is positive, negative, neural or other emotion. Sentiment analysis has been applied for several real-world applications, such as chatbot. In the last five years, the practical use of the chatbot has been prevailing in many field of industry. In the chatbot applications, to recognize the user emotion, sentiment analysis must be performed in advance in order to understand the intent of speakers. The specific emotion is more than describing positive or negative sentences. In light of this context, we propose deep learning models for conducting multi-class sentiment analysis for identifying speaker's emotion which is categorized to be joy, fear, guilt, sad, shame, disgust, and anger. Thus, we develop convolutional neural network (CNN), long short term memory (LSTM), and multi-layer neural network models, as deep neural networks models, for detecting emotion in a sentence. In addition, word embedding process was also applied in our research. In our experiments, we have found that long short term memory (LSTM) model performs best compared to convolutional neural networks and multi-layer neural networks. Moreover, we also show the practical applicability of the deep learning models to the sentiment analysis for chatbot.

• The Journal of Information Systems
• /
• v.30 no.3
• /
• pp.201-216
• /
• 2021

Purpose The purpose of this study is to analyze the trend of patent technology in textile materials using text mining methodology based on Dynamic Embedded Topic Model and Structural Topic Model. It is expected that this study will have positive impact on revitalizing and developing textile materials industry as finding out technology trends. Design/methodology/approach The data used in this study is 866 domestic patent text data in textile material from 1974 to 2020. In order to analyze technology trends from various aspect, Dynamic Embedded Topic Model and Structural Topic Model mechanism were used. The word embedding technique used in DETM is the GloVe technique. For Stable learning of topic modeling, amortized variational inference was performed based on the Recurrent Neural Network. Findings As a result of this analysis, it was found that 'manufacture' topics had the largest share among the six topics. Keyword trend analysis found the fact that natural and nanotechnology have recently been attracting attention. The metadata analysis results showed that manufacture technologies could have a high probability of patent registration in entire time series, but the analysis results in recent years showed that the trend of elasticity and safety technology is increasing.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.