• Journal of Korean Medical classics
• /
• v.32 no.1
• /
• pp.61-74
• /
• 2019

Objectives : The purpose of this study is to help select an appropriate word embedding method when analyzing East Asian traditional medicine texts as data. Methods : Based on prescription data that imply traditional methods in traditional East Asian medicine, we have examined 4 count-based word embedding and 2 prediction-based word embedding methods. In order to intuitively compare these word embedding methods, we proposed a "prescription generating game" and compared its results with those from the application of the 6 methods. Results : When the adjacent vectors are extracted, the count-based word embedding method derives the main herbs that are frequently used in conjunction with each other. On the other hand, in the prediction-based word embedding method, the synonyms of the herbs were derived. Conclusions : Counting based word embedding methods seems to be more effective than prediction-based word embedding methods in analyzing the use of domesticated herbs. Among count-based word embedding methods, the TF-vector method tends to exaggerate the frequency effect, and hence the TF-IDF vector or co-word vector may be a more reasonable choice. Also, the t-score vector may be recommended in search for unusual information that could not be found in frequency. On the other hand, prediction-based embedding seems to be effective when deriving the bases of similar meanings in context.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.60-63
• /
• 2017

자연어처리에 딥 러닝을 적용하기 위해 사용되는 Word embedding은 단어를 벡터 공간상에 표현하는 것으로 차원축소 효과와 더불어 유사한 의미의 단어는 유사한 벡터 값을 갖는다는 장점이 있다. 이러한 word embedding은 대용량 코퍼스를 학습해야 좋은 성능을 얻을 수 있기 때문에 기존에 많이 사용되던 word2vec 모델은 대용량 코퍼스 학습을 위해 모델을 단순화 하여 주로 단어의 등장 비율에 중점적으로 맞추어 학습하게 되어 단어의 위치 정보를 이용하지 않는다는 단점이 있다. 본 논문에서는 기존의 word embedding 학습 모델을 단어의 위치정보를 이용하여 학습 할 수 있도록 수정하였다. 실험 결과 단어의 위치정보를 이용하여 word embedding을 학습 하였을 경우 word-analogy의 syntactic 성능이 크게 향상되며 어순이 바뀔 수 있는 한국어에서 특히 큰 효과를 보였다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.60-63
• /
• 2017

자연어처리에 딥 러닝을 적용하기 위해 사용되는 Word embedding은 단어를 벡터 공간상에 표현하는 것으로 차원축소 효과와 더불어 유사한 의미의 단어는 유사한 벡터 값을 갖는다는 장점이 있다. 이러한 word embedding은 대용량 코퍼스를 학습해야 좋은 성능을 얻을 수 있기 때문에 기존에 많이 사용되던 word2vec 모델은 대용량 코퍼스 학습을 위해 모델을 단순화 하여 주로 단어의 등장 비율에 중점적으로 맞추어 학습하게 되어 단어의 위치 정보를 이용하지 않는다는 단점이 있다. 본 논문에서는 기존의 word embedding 학습 모델을 단어의 위치정보를 이용하여 학습 할 수 있도록 수정하였다. 실험 결과 단어의 위치정보를 이용하여 word embedding을 학습 하였을 경우 word-analogy의 syntactic 성능이 크게 향상되며 어순이 바뀔 수 있는 한국어에서 특히 큰 효과를 보였다.

• Journal of the Korea Convergence Society
• /
• v.9 no.10
• /
• pp.45-53
• /
• 2018

Recently, studies about bilingual word embedding have been gaining much attention. However, bilingual word embedding with Korean is not actively pursued due to the difficulty in obtaining a sizable, high quality corpus. Local embeddings that can be applied to specific domains are relatively rare. Additionally, multi-word vocabulary is problematic due to the lack of one-to-one word-level correspondence in translation pairs. In this paper, we crawl 868,163 paragraphs from a Korean-English law corpus and propose three mapping strategies for word embedding. These strategies address the aforementioned issues including multi-word translation and improve translation pair quality on paragraph-aligned data. We demonstrate a twofold increase in translation pair quality compared to the global bilingual word embedding baseline.

• 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.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.599-612
• /
• 2022

This study focuses on improving a word embedding model to enhance the performance of downstream tasks, such as those of dialog systems. To improve traditional word embedding models, such as skip-gram, it is critical to refine the word features and expand the context model. In this paper, we approach the word model from the perspective of subword embedding and attempt to extend the context model by integrating various sentence models. Our proposed sentence model is a subword-based skip-thought model that integrates self-attention and relative position encoding techniques. We also propose a clustering-based dialog model for downstream task verification and evaluate its relationship with the sentence-model-based subword embedding technique. The proposed subword embedding method produces better results than previous methods in evaluating word and sentence similarity. In addition, the downstream task verification, a clustering-based dialog system, demonstrates an improvement of up to 4.86% over the results of FastText in previous research.

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.179-180
• /
• 2019

Nowadays, clustering algorithm is considered as a promising solution for lacking human-labeled and massive data of social media sites in numerous machine learning tasks. Many researchers propose disaster event detection systems have ability to determine special local events, such as missing people, public transport damage by clustering similar tweets and hashtags together. In this paper, we try to extend tweet hashtag feature definition by applying word embedding. The experimental results are described that word embedding achieve better performance than the reference method.

• Journal of the Korean Society of Safety
• /
• v.36 no.5
• /
• pp.61-70
• /
• 2021

This study aimed to analyze the research trends of the abstract data of ergonomic studies registered in MEDLINE, a medical bibliographic database, using word embedding. Medical-related ergonomic studies mainly focus on work-related musculoskeletal disorders, and there are no studies on the analysis of words as data using natural language processing techniques, such as word embedding. In this study, the abstract data of ergonomic studies were extracted with a program written with selenium and BeutifulSoup modules using python. The word embedding of the abstract data was performed using the word2vec model, after which the data found in the abstract were vectorized. The vectorized data were visualized in two dimensions using t-Distributed Stochastic Neighbor Embedding (t-SNE). The word "ergonomics" and ten of the most frequently used words in the abstract were selected as keywords. The results revealed that the most frequently used words in the abstract of ergonomics studies include "use", "work", and "task". In addition, the t-SNE technique revealed that words, such as "workplace", "design", and "engineering," exhibited the highest relevance to ergonomics. The keywords observed in the abstract of ergonomic studies using t-SNE were classified into four groups. Ergonomics studies registered with MEDLINE have investigated the risk factors associated with workers performing an operation or task using tools, and in this study, ergonomics studies were identified by the relationship between keywords using word embedding. The results of this study will provide useful and diverse insights on future research direction on ergonomic studies.

• The Journal of Information Systems
• /
• v.30 no.2
• /
• pp.57-78
• /
• 2021

Purpose In this study, first, we try to make embedding results that reflect the characteristics of both professional and general documents. In addition, when disparate documents are put together as learning materials for natural language processing, we try to propose a method that can measure the degree of reflection of the characteristics of individual domains in a quantitative way. Approach For this study, the Korean Supreme Court Precedent documents and Korean Wikipedia are selected as specialized documents and general documents respectively. After extracting the most similar word pairs and similarities of unique words observed only in the specialized documents, we observed how those values were changed in the process of embedding with general documents. Findings According to the measurement methods proposed in this study, it was confirmed that the degree of specificity of specialized documents was relaxed in the process of combining with general documents, and that the degree of dissolution could have a positive correlation with the size of general documents.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.389-399
• /
• 2021

In recent years, word embedding has been a popular field of natural language processing research and a skip-gram has become one successful word embedding method. It assigns a word embedding vector to each word using contexts, which provides an effective way to analyze text data. However, due to the limitation of vector space model, primary word embedding methods assume that every word only have a single meaning. As one faces multi-sense words, that is, words with more than one meaning, in reality, Neelakantan (2014) proposed a multi-sense skip-gram (MSSG) to find embedding vectors corresponding to the each senses of a multi-sense word using a clustering method. In this paper, we propose a modified method of the MSSG to improve statistical accuracy. Moreover, we propose a data-adaptive choice of the number of clusters, that is, the number of meanings for a multi-sense word. Some numerical evidence is given by conducting real data-based simulations.