• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.226-231
• /
• 2017

Word representation, an important area in natural language processing(NLP) used machine learning, is a method that represents a word not by text but by distinguishable symbol. Existing word embedding employed a large number of corpora to ensure that words are positioned nearby within text. However corpus-based word embedding needs several corpora because of the frequency of word occurrence and increased number of words. In this paper word embedding is done using dictionary definitions and semantic relationship information(hypernyms and antonyms). Words are trained using the feature mirror model(FMM), a modified Skip-Gram(Word2Vec). Sense similar words have similar vector. Furthermore, it was possible to distinguish vectors of antonym words.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.399-403
• /
• 2022

Natural texts are analyzed to obtain their intended meaning to be classified depending on the problem under study. One way to represent words is by generating vectors of real values to encode the meaning; this is called word embedding. Similarities between word representations are measured to identify text class. Word embeddings can be created using word2vec technique. However, recently fastText was implemented to provide better results when it is used with classifiers. In this paper, we will study the performance of well-known classifiers when using both techniques for word embedding with Arabic dataset. We applied them to real data collected from Wikipedia, and we found that both word2vec and fastText had similar accuracy with all used classifiers.

• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.493-501
• /
• 2022

This paper is a study on context-sensitive spelling error correction and uses the Korean WordNet (KorLex)[1] that defines the relationship between words as a graph to improve the performance of the correction[2] based on the vector information of the word embedded in the correction technique. The Korean WordNet replaced WordNet[3] developed at Princeton University in the United States and was additionally constructed for Korean. In order to learn a semantic network in graph form or to use it for learned vector information, it is necessary to transform it into a vector form by embedding learning. For transformation, we list the nodes (limited number) in a line format like a sentence in a graph in the form of a network before the training input. One of the learning techniques that use this strategy is Deepwalk[4]. DeepWalk is used to learn graphs between words in the Korean WordNet. The graph embedding information is used in concatenation with the word vector information of the learned language model for correction, and the final correction word is determined by the cosine distance value between the vectors. In this paper, In order to test whether the information of graph embedding affects the improvement of the performance of context- sensitive spelling error correction, a confused word pair was constructed and tested from the perspective of Word Sense Disambiguation(WSD). In the experimental results, the average correction performance of all confused word pairs was improved by 2.24% compared to the baseline correction performance.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.468-475
• /
• 2020

A good acoustic word embedding that can well express the characteristics of word plays an important role in wake-up word detection (WWD). However, the representation ability of acoustic word embedding may be weakened due to various types of environmental noise occurred in the place where WWD works, causing performance degradation. In this paper, we proposed triplet loss based Domain Adversarial Training (tDAT) mitigating environmental factors that can affect acoustic word embedding. Through experiments in noisy environments, we verified that the proposed method effectively improves the conventional DAT approach, and checked its scalability by combining with other method proposed for robust WWD.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.254-276
• /
• 2019

Since the amount of information on the internet is growing rapidly, it is not easy for a user to find relevant information for his/her query. To tackle this issue, the researchers are paying much attention to Document Summarization. The key point in any successful document summarizer is a good document representation. The traditional approaches based on word overlapping mostly fail to produce that kind of representation. Word embedding has shown good performance allowing words to match on a semantic level. Naively concatenating word embeddings makes common words dominant which in turn diminish the representation quality. In this paper, we employ word embeddings to improve the weighting schemes for calculating the Latent Semantic Analysis input matrix. Two embedding-based weighting schemes are proposed and then combined to calculate the values of this matrix. They are modified versions of the augment weight and the entropy frequency that combine the strength of traditional weighting schemes and word embedding. The proposed approach is evaluated on three English datasets, DUC 2002, DUC 2004 and Multilingual 2015 Single-document Summarization. Experimental results on the three datasets show that the proposed model achieved competitive performance compared to the state-of-the-art leading to a conclusion that it provides a better document representation and a better document summary as a result.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.24-29
• /
• 2018

Text analysis technique for natural language processing in deep learning represents words in vector form through word embedding. In this paper, we propose a method of constructing a document vector and classifying it into spam and normal text message, using word embedding and deep learning method. Automatic spacing applied in the preprocessing process ensures that words with similar context are adjacently represented in vector space. Additionally, the intentional word formation errors with non-alphabetic or extraordinary characters are designed to avoid being blocked by spam message filter. Two embedding algorithms, CBOW and skip grams, are used to produce the sentence vector and the performance and the accuracy of deep learning based spam filter model are measured by comparing to those of SVM Light.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.8
• /
• pp.181-188
• /
• 2020

In this study, we propose a comparative study to confirm the impact of various word embedding techniques on the performance of sentiment analysis. Sentiment analysis is one of opinion mining techniques to identify and extract subjective information from text using natural language processing and can be used to classify the sentiment of product reviews or comments. Since sentiment can be classified as either positive or negative, it can be considered one of the general classification problems. For sentiment analysis, the text must be converted into a language that can be recognized by a computer. Therefore, text such as a word or document is transformed into a vector in natural language processing called word embedding. Various techniques, such as Bag of Words, TF-IDF, and Word2Vec are used as word embedding techniques. Until now, there have not been many studies on word embedding techniques suitable for emotional analysis. In this study, among various word embedding techniques, Bag of Words, TF-IDF, and Word2Vec are used to compare and analyze the performance of movie review sentiment analysis. The research data set for this study is the IMDB data set, which is widely used in text mining. As a result, it was found that the performance of TF-IDF and Bag of Words was superior to that of Word2Vec and TF-IDF performed better than Bag of Words, but the difference was not very significant.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.9
• /
• pp.317-325
• /
• 2017

In this paper, we try to classify Korean hedge sentences, which are regarded as not important since they express uncertainties or personal assumptions. Through previous researches to English language, we found dependency information of words has been one of important features in hedge classification, but not used in Korean researches. Additionally, we found that word embedding vectors include the word usage information. We assume that the word usage information could somehow represent the dependency information. Therefore, we utilized word embedding and neural networks in hedge sentence classification. We used more than one and half million sentences as word embedding dataset and also manually constructed 12,517-sentence hedge classification dataset obtained from online news. We used SVM and CRF as our baseline systems and the proposed system outperformed SVM by 7.2%p and also CRF by 1.2%p. This indicates that word usage information has positive impacts on Korean hedge classification.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.510-513
• /
• 2018

본 논문은 다양한 워드 임베딩 모델(word embedding model)들과 하이퍼 파라미터(hyper parameter)들을 조합하였을 때 특정 영역에 어떠한 성능을 보여주는지에 대한 연구이다. 3 가지의 워드 임베딩 모델인 Word2Vec, FastText, Glove의 차원(dimension)과 윈도우 사이즈(window size), 최소 횟수(min count)를 각기 달리하여 총 36개의 임베딩 벡터(embedding vector)를 만들었다. 각 임베딩 벡터를 Fast and Accurate Dependency Parser 모델에 적용하여 각 모들의 성능을 측정하였다. 모든 모델에서 차원이 높을수록 성능이 개선되었으며, FastText가 대부분의 경우에서 높은 성능을 내는 것을 알 수 있었다.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1391-1402
• /
• 2021

This paper focuses use context-sensitive spelling error correction using generative adversarial network. Generative adversarial network[1] are attracting attention as they solve data generation problems that have been a challenge in the field of deep learning. In this paper, sentences are generated using word embedding information and reflected in word distribution representation. We experiment with DCGAN[2] used for the stability of learning in the existing image processing and D2GAN[3] with double discriminator. In this paper, we experimented with how the composition of generative adversarial networks and the change of learning corpus influence the context-sensitive spelling error correction In the experiment, we correction the generated word embedding information and compare the performance with the actual word embedding information.