• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.31-41
• /
• 2018

Text classification has been studied for a long time in the Natural Language Processing field. In this paper, we propose an article- and paragraph-level genre classification system using Word2Vec-based LSTM, GRU, and CNN models for large-scale English corpora. Both article- and paragraph-level classification performed best in accuracy with LSTM, which was followed by GRU and CNN in accuracy performance. Thus, it is to be confirmed that in evaluating the classification performance of LSTM, GRU, and CNN, the word sequential information for articles is better than the word feature extraction for paragraphs when the pre-trained Word2Vec-based word embeddings are used in both deep learning-based article- and paragraph-level classification tasks.

• Journal of the Korean Society for information Management
• /
• v.40 no.4
• /
• pp.307-327
• /
• 2023

To analyze the impact of word embedding on book titles, this study utilized word embedding models (Word2vec, GloVe, fastText) to generate embedding vectors from book titles. These vectors were then used as classification features for automatic classification. The classifier utilized the k-nearest neighbors (kNN) algorithm, with the categories for automatic classification based on the DDC (Dewey Decimal Classification) main class 300 assigned by libraries to books. In the automatic classification experiment applying word embeddings to book titles, the Skip-gram architectures of Word2vec and fastText showed better results in the automatic classification performance of the kNN classifier compared to the TF-IDF features. In the optimization of various hyperparameters across the three models, the Skip-gram architecture of the fastText model demonstrated overall good performance. Specifically, better performance was observed when using hierarchical softmax and larger embedding dimensions as hyperparameters in this model. From a performance perspective, fastText can generate embeddings for substrings or subwords using the n-gram method, which has been shown to increase recall. The Skip-gram architecture of the Word2vec model generally showed good performance at low dimensions(size 300) and with small sizes of negative sampling (3 or 5).

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.771-788
• /
• 2019

Deep learning techniques such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) show superior performance in text classification than traditional approaches such as Support Vector Machines (SVMs) and Naïve Bayesian approaches. When using CNNs for text classification tasks, word embedding or character embedding is a step to transform words or characters to fixed size vectors before feeding them into convolutional layers. In this paper, we propose a parallel word-level and character-level embedding approach in CNNs for text classification. The proposed approach can capture word-level and character-level patterns concurrently in CNNs. To show the usefulness of proposed approach, we perform experiments with two English and three Korean text datasets. The experimental results show that character-level embedding works better in Korean and word-level embedding performs well in English. Also the experimental results reveal that the proposed approach provides better performance than traditional CNNs with word-level embedding or character-level embedding in both Korean and English documents. From more detail investigation, we find that the proposed approach tends to perform better when there is relatively small amount of data comparing to the traditional embedding approaches.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.742-751
• /
• 2005

This paper proposes a novel text image watermarking algorithm based on word classification. The words are classified into K classes using simple features. Several adjacent words are grouped into a segment. and the segments are also classified using the word class information. The same amount of information is inserted into each of the segment classes. The signal is encoded by modifying some inter-word spaces statistics of segment classes. Subjective comparisons with conventional word-shift algorithms are presented under several criteria.

• Journal of KIISE
• /
• v.43 no.6
• /
• pp.678-685
• /
• 2016

Named Entity Recognition and Classification (NERC) is a task for recognition and classification of named entities such as a person's name, location, and organization. There have been various studies carried out on Korean NERC, but they have some problems, for example lacking some features as compared with English NERC. In this paper, we propose a method that uses word embedding as features for Korean NERC. We generate a word vector using a Continuous-Bag-of-Word (CBOW) model from POS-tagged corpus, and a word cluster symbol using a K-means algorithm from a word vector. We use the word vector and word cluster symbol as word embedding features in Conditional Random Fields (CRFs). From the result of the experiment, performance improved 1.17%, 0.61% and 1.19% respectively for TV domain, Sports domain and IT domain over the baseline system. Showing better performance than other NERC systems, we demonstrate the effectiveness and efficiency of the proposed method.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.133-140
• /
• 2018

Accurate sentiment classification is an important research topic in sentiment analysis. This study suggests an efficient classification method of Korean sentiment using word2vec and ensemble methods which have been recently studied variously. For the 200,000 Korean movie review texts, we generate a POS-based BOW feature and a feature using word2vec, and integrated features of two feature representation. We used a single classifier of Logistic Regression, Decision Tree, Naive Bayes, and Support Vector Machine and an ensemble classifier of Adaptive Boost, Bagging, Gradient Boosting, and Random Forest for sentiment classification. As a result of this study, the integrated feature representation composed of BOW feature including adjective and adverb and word2vec feature showed the highest sentiment classification accuracy. Empirical results show that SVM, a single classifier, has the highest performance but ensemble classifiers show similar or slightly lower performance than the single classifier.

• Journal of the Korean Society for Library and Information Science
• /
• v.44 no.4
• /
• pp.179-201
• /
• 2010

This study aims to analyze the word based classification used in U.S. public libraries and their implications for Korean libraries. For this purpose, eleven U.S. public libraries using the word based classification system were selected and the specific classification types, their motivation, collection size, methods used in the conversion from DDC, and pros and cons were examined. The result of the analysis shows that the word based classification system may be categorized into the two types: Dewey-free or Dewey-lite and its application methods are different case by case. As a result, the positive impacts and implied problems of the word based classification system for library use and library operation were examined. In addition, the new system's implications on the Korean libraries were also discussed.

• The KIPS Transactions:PartB
• /
• v.18B no.2
• /
• pp.93-108
• /
• 2011

We propose a extended vector space model by using ambiguous words and disambiguous words to improve the result of a Korean document classification method. In this paper we study the precision enhancement of vector space model and we propose a new axis that represents a weight value. Conventional classification methods without the weight value had some problems in vector comparison. We define a word which has same axis of the weight value as ambiguous word after calculating a mutual information value between a term and its classification field. We define a word which is disambiguous with ambiguous meaning as disambiguous word. We decide the strengthness of a disambiguous word among several words which is occurring ambiguous word and a same document. Finally, we proposed a new classification method based on extension of vector dimension with ambiguous and disambiguous words.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.563-568
• /
• 2016

The word sense disambiguation problem is to find the correct sense of an ambiguous word having multiple senses in a dictionary in a sentence. We regard this problem as a multi-class classification problem and classify the ambiguous word by using Support Vector Machines. Context words of the ambiguous word, which are extracted from Sejong sense tagged corpus, are represented to two kinds of vector space. One vector space is composed of context words vectors having binary weights. The other vector space has vectors where the context words are mapped by word embedding model. After experiments, we acquired accuracy of 87.0% with context word vectors and 86.0% with word embedding model.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1290-1295
• /
• 2017

Document classification, a task of classifying the category of each document based on text, is one of the fundamental areas for natural language processing. Document classification may be used in various fields such as topic classification and sentiment classification. Neural network models for document classification can be divided into two categories: word-level models and character-level models that treat words and characters as basic units respectively. In this study, we propose a neural network model that combines character-level and word-level models to improve performance of document classification. The proposed model extracts the feature vector of each word by combining information obtained from a word embedding matrix and information encoded by a character-level neural network. Based on feature vectors of words, the model classifies documents with a hierarchical structure wherein recurrent neural networks with attention mechanisms are used for both the word and the sentence levels. Experiments on real life datasets demonstrate effectiveness of our proposed model.