• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1014-1017
• /
• 2020

Many natural language processing (NLP) models utilize pre-trained word embeddings to leverage latent information. One of the most successful word embedding model is the Skip-gram (SG). In this paper, we propose a Skipgram drop (SG-Drop) model, which is a variation of the SG model. The SG-Drop model is designed to reduce training time efficiently. Furthermore, the SG-Drop allows controlling training time with its hyperparameter. It could train word embedding faster than reducing training epochs while better preserving the quality.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.494-497
• /
• 2021

텍스트 분류(text classification)는 원시 텍스트 데이터로부터 정보를 추출할 수 있는 기술에 기반하여 많은 양의 텍스트 데이터를 관심 영역으로 분류하는 것으로 최근에 각광을 받고 있다. 본 논문에서는 워드 임베딩(word embedding) 기법을 이용하여 특정 분야의 연구 논문을 분류하고 추천하는 기법을 제안한다. 워드 임베딩으로 CBOW(Continuous Bag-of-Word)와 Sg(Skip-gram)를 연구 논문의 분류에 적용하고 기존 방식인 TF-IDF(Term Frequency-Inverse Document Frequency)와 성능을 비교 분석한다. 성능 평가 결과는 워드 임베딩에 기반한 연구 논문 분류 기법이 TF-IDF에 기반한 연구 논문 분류 기법보다 좋은 성능을 가진다는 것을 나타낸다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.5
• /
• pp.1027-1037
• /
• 2019

Conventional cyber-attack detection solutions are generally based on signature-based or malicious behavior analysis so that have had difficulty in detecting unknown method-based attacks. Since the various information occurring all the time reflects the state of the system, by modeling it in a steady state and detecting an abnormal state, an unknown attack can be detected. Since a variety of system information occurs in a string form, word embedding, ie, techniques for converting strings into vectors preserving their order and semantics, can be used for modeling and detection. Novelty Detection, which is a technique for detecting a small number of abnormal data in a plurality of normal data, can be performed in order to detect an abnormal condition. This paper proposes a method to detect system anomaly by cyber attack using embedding and novelty detection.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.93-102
• /
• 2022

Dependency parsing is a decision problem of the syntactic relation between words in a sentence. Recently, deep learning models are used for dependency parsing based on the word representations in a continuous vector space. However, it causes a mislabeled tagging problem for the proper nouns that rarely appear in the training corpus because it is difficult to express out-of-vocabulary (OOV) words in a continuous vector space. To solve the OOV problem in dependency parsing, we explored the proper noun embedding method according to the embedding unit. Before representing words in a continuous vector space, we replace the proper nouns with a special token and train them for the contextual features by using the multi-layer bidirectional LSTM. Two models of the syllable-based and morpheme-based unit are proposed for proper noun embedding and the performance of the dependency parsing is more improved in the ensemble model than each syllable and morpheme embedding model. The experimental results showed that our ensemble model improved 1.69%p in UAS and 2.17%p in LAS than the same arc-eager approach-based Malt parser.

• Journal of the Korea Convergence Society
• /
• v.11 no.11
• /
• pp.33-39
• /
• 2020

In the field of Natural Language Processing, Various research such as Translation, POS Tagging, Q&A, and Sentiment Analysis are globally being carried out. Sentiment Analysis shows high classification performance for English single-domain datasets by pretrained sentence embedding models. In this thesis, the classification performance is compared by Korean E-commerce online dataset with various domain attributes and 6 Neural-Net models are built as BOW (Bag Of Word), LSTM[1], Attention, CNN[2], ELMo[3], and BERT(KoBERT)[4]. It has been confirmed that the performance of pretrained sentence embedding models are higher than word embedding models. In addition, practical Neural-Net model composition is proposed after comparing classification performance on dataset with 17 categories. Furthermore, the way of compressing sentence embedding model is mentioned as future work, considering inference time against model capacity on real-time service.

• Journal of Convergence for Information Technology
• /
• v.12 no.2
• /
• pp.47-53
• /
• 2022

Recently, with the change of the intelligent security paradigm, study to apply various information generated from various information security systems to AI-based anomaly detection is increasing. Therefore, in this study, in order to convert log-like time series data into a vector, which is a numerical feature, the CBOW and Skip-gram inference methods of deep learning-based Word2Vec model and statistical method based on the coincidence frequency were used to transform the published ADFA system call data. In relation to this, an experiment was carried out through conversion into various embedding vectors considering the dimension of vector, the length of sequence, and the window size. In addition, the performance of the embedding methods used as well as the detection performance were compared and evaluated through GRU-based anomaly detection model using vectors generated by the embedding model as an input. Compared to the statistical model, it was confirmed that the Skip-gram maintains more stable performance without biasing a specific window size or sequence length, and is more effective in making each event of sequence data into an embedding vector.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.413-425
• /
• 2022

The study of literary texts is one of the earliest disciplines practiced around the globe. Poetry is artistic writing in which words are carefully chosen and arranged for their meaning, sound, and rhythm. Poetry usually has a broad and profound sense that makes it difficult to be interpreted even by humans. The essence of poetry is Rasa, which signifies mood or emotion. In this paper, we propose a poetry classification-based approach to automatically extract similar poems from a repository. Specifically, we perform a novel Rasa-based classification of Hindi poetry. For the task, we primarily used lexical features in a bag-of-words model trained using the support vector machine classifier. In the model, we employed Hindi WordNet, Latent Semantic Indexing, and Word2Vec-based neural word embedding. To extract the rich feature vectors, we prepared a repository containing 37 717 poems collected from various sources. We evaluated the performance of the system on a manually constructed dataset containing 945 Hindi poems. Experimental results demonstrated that the proposed model attained satisfactory performance.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.1-11
• /
• 2021

The purpose of this study was to analyze the trends and characteristics of 'stress urinary incontinence' research through word frequency analysis, and their relationships were modeled using word embedding. Abstract data of 9,868 papers containing abstracts in PubMed's MEDLINE were extracted using a Python program. Then, through frequency analysis, 10 keywords were selected according to the high frequency. The similarity of words related to keywords was analyzed by Word2Vec machine learning algorithm. The locations and distances of words were visualized using the t-SNE technique, and the groups were classified and analyzed. The number of studies related to stress urinary incontinence has increased rapidly since the 1980s. The keywords used most frequently in the abstract of the paper were 'woman', 'urethra', and 'surgery'. Through Word2Vec modeling, words such as 'female', 'urge', and 'symptom' were among the words that showed the highest relevance to the keywords in the study on stress urinary incontinence. In addition, through the t-SNE technique, keywords and related words could be classified into three groups focusing on symptoms, anatomical characteristics, and surgical interventions of stress urinary incontinence. This study is the first to examine trends in stress urinary incontinence-related studies using the keyword frequency analysis and word embedding of the abstract. The results of this study can be used as a basis for future researchers to select the subject and direction of the research field related to stress urinary incontinence.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.4
• /
• pp.621-625
• /
• 2018

This paper proposes a method for bridge damage factor recognition from inspection reports using deep learning. Bridge inspection reports contains inspection results including identified damages and causal analysis results. However, collecting such information from inspection reports manually is limited due to their considerable amount. Therefore, this paper proposes a model for recognizing bridge damage factor from inspection reports applying Named Entity Recognition (NER) using deep learning. Named Entity Recognition, Word Embedding, Recurrent Neural Network, one of deep learning methods, were applied to construct the proposed model. Experimental results showed that the proposed model has abilities to 1) recognize damage and damage factor included in a training data, 2) distinguish a specific word as a damage or a damage factor, depending on its context, and 3) recognize new damage words not included in a training data.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.541-548
• /
• 2016

The use of social media is already essential as a source of information for listening user's various opinions and monitoring. We define social 'risks' that issues effect negative influences for public opinion in social media. This paper aims to discriminate various linguistic features and reveal their effects for building an automatic classification model of social risks. Expecially we adopt a word embedding technique for representation of linguistic clues in risk sentences. As a preliminary experiment to analyze characteristics of individual features, we revise errors in automatic linguistic analysis. At the result, the most important feature is NE (Named Entity) information and the best condition is when combine basic linguistic features. word embedding, and word clusters within core predicates. Experimental results under the real situation in social bigdata - including linguistic analysis errors - show 92.08% and 85.84% in precision respectively for frequent risk categories set and full test set.