• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.137-142
• /
• 2017

원격 지도 학습은 자동으로 매우 큰 코퍼스와 지식베이스 간의 주석 데이터를 생성하여 기계 학습에 필요한 학습 데이터를 사람의 손을 빌리지 않고 저렴한 비용으로 만들 수 있어, 많은 연구들이 관계 추출 문제를 해결하기 위해 원격 지도 학습 방법을 적용하고 있다. 그러나 기존 연구들에서는 모델 학습의 입력으로 사용되는 단어 임베딩에서 단어의 동형이의어 성질을 반영하지 못한다는 단점이 있다. 때문에 서로 다른 의미를 가진 동형이의어가 하나의 임베딩 값을 가지다 보니, 단어의 의미를 정확히 파악하지 못한 채 관계 추출 모델을 학습한다고 볼 수 있다. 본 논문에서는 원격 지도 학습 기반 관계 추출 모델에 다중-어의 단어 임베딩을 적용한 모델을 제안한다. 다중-어의 단어 임베딩 학습을 위해 어의 중의성 해소 모듈을 활용하였으며, 관계 추출 모델은 문장 내 주요 특징을 효율적으로 파악하는 모델인 CNN과 PCNN을 활용하였다. 본 논문에서 제안하는 다중-어의 단어 임베딩 적용 관계추출 모델의 성능을 평가하기 위해 추가적으로 2가지 방식의 단어 임베딩을 학습하여 비교 평가를 수행하였고, 그 결과 어의 중의성 해소 모듈을 활용한 단어 임베딩을 활용하였을 때 관계추출 모델의 성능이 향상된 결과를 보였다.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.11a
• /
• pp.40-41
• /
• 2019

The purpose of this study is to analyze the vocabulary related to safety accidents based on the reports recorded on the violation of safety rules at the construction sites. We used Word2Vec and Topic Model as natural language processing techniques to analyze the safety accidents presented in the reports of the large enterprise. The words that appeared based on the occupational accident types such as the fall, falling objects, and others were derived and visualized. We derive the frequency and similarity of the words and topics of the accident that occur at the construction site. In future studies, we will be able to proceed with the generation of texts from pictures based on images and this reports.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.2
• /
• pp.139-151
• /
• 2020

Entity name recognition is a part of information extraction that extracts entity names from documents and classifies the types of extracted entity names. Entity name recognition technologies are widely used in natural language processing, such as information retrieval, machine translation, and query response systems. Various deep learning-based models exist to improve entity name recognition performance, but studies that compared and analyzed these models on Korean data are insufficient. In this paper, we compare and analyze the performance of CRF, LSTM-CRF, BiLSTM-CRF, and BERT, which are actively used to identify entity names using Korean data. Also, we compare and evaluate whether embedding models, which are variously used in recent natural language processing tasks, can affect the entity name recognition model's performance improvement. As a result of experiments on patent data and Korean corpus, it was confirmed that the BiLSTM-CRF using FastText method showed the highest performance.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.2
• /
• pp.179-199
• /
• 2019

In this paper, we propose optimal methodologies for classifying patent literature by examining various feature extraction methods, machine learning and deep learning models, and provide optimal performance through experiments. We compared the traditional BoW method and a distributed representation method (word embedding vector) as a feature extraction, and compared the morphological analysis and multi gram as the method of constructing the document collection. In addition, classification performance was verified using traditional machine learning model and deep learning model. Experimental results show that the best performance is achieved when we apply the deep learning model with distributed representation and morphological analysis based feature extraction. In Section, Class and Subclass classification experiments, We improved the performance by 5.71%, 18.84% and 21.53%, respectively, compared with traditional classification methods.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.127-146
• /
• 2021

Fake news isexpanded and reproduced rapidly regardless of their authenticity by the characteristics of modern society, called the information age. Assuming that 1% of all news are fake news, the amount of economic costs is reported to about 30 trillion Korean won. This shows that the fake news isvery important social and economic issue. Therefore, this study aims to develop an automated detection model to quickly and accurately verify the authenticity of the news. To this end, this study crawled the news data whose authenticity is verified, and developed fake news prediction models using word embedding (Word2Vec, Fasttext) and deep learning algorithms (LSTM, BiLSTM). Experimental results show that the prediction model using BiLSTM with Word2Vec achieved the best accuracy of 84%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.9
• /
• pp.4568-4584
• /
• 2016

Steganography based on text generation has become a hot research topic in recent years. However, current text-generation methods which generate texts of normal style have either semantic or syntactic flaws. Note that texts of special genre, such as poem, have much simpler language model, less grammar rules, and lower demand for naturalness. Motivated by this observation, in this paper, we propose a text steganography that utilizes Markov chain model to generate Ci-poetry, a classic Chinese poem style. Since all Ci poems have fixed tone patterns, the generation process is to select proper words based on a chosen tone pattern. Markov chain model can obtain a state transfer matrix which simulates the language model of Ci-poetry by learning from a given corpus. To begin with an initial word, we can hide secret message when we use the state transfer matrix to choose a next word, and iterating until the end of the whole Ci poem. Extensive experiments are conducted and both machine and human evaluation results show that our method can generate Ci-poetry with higher naturalness than former researches and achieve competitive embedding rate.

• Communications for Statistical Applications and Methods
• /
• v.30 no.5
• /
• pp.485-499
• /
• 2023

This study aimed to predict the number of meals served in a group cafeteria using machine learning methodology. Features of the menu were created through the Word2Vec methodology and clustering, and a stacking ensemble model was constructed using Random Forest, Gradient Boosting, and CatBoost as sub-models. Results showed that CatBoost had the best performance with the ensemble model showing an 8% improvement in performance. The study also found that the date variable had the greatest influence on the number of diners in a cafeteria, followed by menu characteristics and other variables. The implications of the study include the potential for machine learning methodology to improve predictive performance and reduce food waste, as well as the removal of subjective elements in menu classification. Limitations of the research include limited data cases and a weak model structure when new menus or foreign words are not included in the learning data. Future studies should aim to address these limitations.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.93-110
• /
• 2023

Recently, attempts have been made to convert unstructured text into vectors and to analyze vast amounts of natural language for various purposes. In particular, the demand for analyzing texts in specialized domains is rapidly increasing. Therefore, studies are being conducted to analyze specialized and general-purpose documents simultaneously. To analyze specific terms with general terms, it is necessary to align the embedding space of the specific terms with the embedding space of the general terms. So far, attempts have been made to align the embedding of specific terms into the embedding space of general terms through a transformation matrix or mapping function. However, the linear transformation based on the transformation matrix showed a limitation in that it only works well in a local range. To overcome this limitation, various types of nonlinear vector alignment methods have been recently proposed. We propose a vector alignment model that matches the embedding space of specific terms to the embedding space of general terms through end-to-end learning that simultaneously learns the autoencoder and regression model. As a result of experiments with R&D documents in the "Healthcare" field, we confirmed the proposed methodology showed superior performance in terms of accuracy compared to the traditional model.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.48-57
• /
• 2019

The purpose of this study is to understand the intention of the inquirer from the single text type question in Goal-oriented dialogue. Goal-Oriented Dialogue system means a dialogue system that satisfies the user's specific needs via text or voice. The intention analysis process is a step of analysing the user's intention of inquiry prior to the answer generation, and has a great influence on the performance of the entire Goal-Oriented Dialogue system. The proposed model was used for a daily chemical products domain and Korean text data related to the domain was used. The analysis is divided into a speech-act which means independent on a specific field concept-sequence and which means depend on a specific field. We propose a classification method using the word embedding model and the CNN as a method for analyzing speech-act and concept-sequence. The semantic information of the word is abstracted through the word embedding model, and concept-sequence and speech-act classification are performed through the CNN based on the semantic information of the abstract word.