• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.441-445
• /
• 2020

토큰화(Tokenization)는 사람이 작성한 자연어 문장을 기계가 잘 이해할 수 있도록 최소 단위인 토큰으로 분리하는 작업을 말하여, 이러한 토큰화는 자연어처리 전반적인 태스크들의 전처리에 필수적으로 사용되고 있다. 최근 자연어처리 분야에서 높은 성능을 보이며, 다양한 딥러닝 모델에 많이 활용되고 있는 SentencePiece 토큰화는 여러 단어에서 공통적으로 출현하는 부분단어들을 기준으로, BPE 알고리즘을 이용하여 문장을 압축 표현하는 토큰화 방법이다. 본 논문에서는 한국어 기반 특허 문헌의 초록 자연어 데이터를 기반으로 SentencePiece를 비롯한 여러 토큰화 방법에 대하여 소개하며, 해당 방법을 응용한 기계번역 (Neural Machine Translation) 태스크를 수행하고, 토큰화 방법별 비교 평가를 통해 특허 분야 자연어 데이터에 최적화된 토큰화 방법을 제안한다. 그리고 본 논문에서 제안한 방법을 사용하여 특허 초록 한-영 기계번역 태스크에서 성능이 향상됨을 보였다.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.76-85
• /
• 2007

This paper addresses a task of opinion extraction from given documents and its positive/negative classification. We propose a sentence classification method using a notion of syntactic piece. Syntactic piece is a minimum unit of structure, and is used as an alternative processing unit of n-gram and whole tree structure. We compute its semantic orientation, and classify opinion sentences into positive or negative. We have conducted an experiment on more than 5000 opinion sentences of multiple domains, and have proven that our approach attains high performance at 91% precision.

• Journal of Korean Society for Quality Management
• /
• v.48 no.3
• /
• pp.421-431
• /
• 2020

Purpose: The purpose of this study is to compare and analyze the tokenizer in natural language processing for customer satisfaction in sentiment analysis. Methods: In this study, a supervised learning-based tokenizer Mecab-Ko and an unsupervised learning-based tokenizer SentencePiece were used for comparison. Three algorithms: Naïve Bayes, k-Nearest Neighbor, and Decision Tree were selected to compare the performance of each tokenizer. For performance comparison, three metrics: accuracy, precision, and recall were used in the study. Results: The results of this study are as follows; Through performance evaluation and verification, it was confirmed that SentencePiece shows better classification performance than Mecab-Ko. In order to confirm the robustness of the derived results, independent t-tests were conducted on the evaluation results for the two types of the tokenizer. As a result of the study, it was confirmed that the classification performance of the SentencePiece tokenizer was high in the k-Nearest Neighbor and Decision Tree algorithms. In addition, the Decision Tree showed slightly higher accuracy among the three classification algorithms. Conclusion: The SentencePiece tokenizer can be used to classify and interpret customer sentiment based on online reviews in Korean more accurately. In addition, it seems that it is possible to give a specific meaning to a short word or a jargon, which is often used by users when evaluating products but is not defined in advance.

• The KIPS Transactions:PartB
• /
• v.14B no.1 s.111
• /
• pp.33-42
• /
• 2007

This paper presents a new methodology for music structure analysis which facilitates rhetoric-based music summarization. Similarity analysis of musical constituents suggests the structure of a musical piece. We can recognize its musical form from the structure. Musical forms have rhetorical characteristics of their on. We have utilized the characteristics for locating musical motifs. Motif extraction is to music summarization what topic sentence extraction is to text summarization. We have evaluated the effectiveness of this methodology through a popular music case study.

• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.149-160
• /
• 2017

Sentiment analysis is the process of determining whether a piece of document, text or conversation is positive, negative, neural or other emotion. Sentiment analysis has been applied for several real-world applications, such as chatbot. In the last five years, the practical use of the chatbot has been prevailing in many field of industry. In the chatbot applications, to recognize the user emotion, sentiment analysis must be performed in advance in order to understand the intent of speakers. The specific emotion is more than describing positive or negative sentences. In light of this context, we propose deep learning models for conducting multi-class sentiment analysis for identifying speaker's emotion which is categorized to be joy, fear, guilt, sad, shame, disgust, and anger. Thus, we develop convolutional neural network (CNN), long short term memory (LSTM), and multi-layer neural network models, as deep neural networks models, for detecting emotion in a sentence. In addition, word embedding process was also applied in our research. In our experiments, we have found that long short term memory (LSTM) model performs best compared to convolutional neural networks and multi-layer neural networks. Moreover, we also show the practical applicability of the deep learning models to the sentiment analysis for chatbot.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.221-224
• /
• 2019

딥러닝을 이용한 Neural Machine Translation(NMT)의 등장으로 기계번역 분야에서 기존의 규칙 기반,통계기반 방식을 압도하는 좋은 성능을 보이고 있다. 본 논문은 기계번역 모델도 중요하지만 무엇보다 중요한 것은 고품질의 학습데이터를 구성하는 일과 전처리라고 판단하여 이에 관련된 다양한 실험을 진행하였다. 인공신경망 기계번역 시스템의 학습데이터 즉 병렬 코퍼스를 구축할 때 양질의 데이터를 확보하는 것이 무엇보다 중요하다. 그러나 양질의 데이터를 구하는 일은 저작권 확보의 문제, 병렬 말뭉치 구축의 어려움, 노이즈 등을 이유로 쉽지 않은 상황이다. 본 논문은 고품질의 학습데이터를 구축하기 위하여 병렬 코퍼스 필터링 기법을 제시한다. 병렬 코퍼스 필터링이란 정제와 다르게 학습 데이터에 부합하지 않다고 판단되며 소스, 타겟 쌍을 함께 삭제 시켜 버린다. 또한 기계번역에서 무엇보다 중요한 단계는 바로 Subword Tokenization 단계이다. 본 논문은 다양한 실험을 통하여 한-영 기계번역에서 가장 높은 성능을 보이는 Subword Tokenization 방법론을 제시한다. 오픈 된 한-영 병렬 말뭉치로 실험을 진행한 결과 병렬 코퍼스 필터링을 진행한 데이터로 만든 모델이 더 좋은 BLEU 점수를 보였으며 본 논문에서 제안하는 형태소 분석 단위 분리를 진행 후 Unigram이 반영된 SentencePiece 모델로 Subword Tokenization를 진행 하였을 시 가장 좋은 성능을 보였다.

• Fashion & Textile Research Journal
• /
• v.12 no.1
• /
• pp.10-20
• /
• 2010

In this research, by yearly subdividing and analyzing the characteristic of the embroidery design according to the garment item with a season the high value added is raised for a differencing and high performance conversion of the high fashion design and there is an object. In 2004, when the total 474 chapter was selected in S/S season till F/W season in 2008 and the embroidery design characteristic according to the kind of an item the analyzing method and statistical method was used. As to the first, and the embroidery design in which it follows of the garment item showed the stylized, and the plant motive of the geometric pattern by an edge and composite arrangement in an one-piece and blouse with the satin stitch and cut work technique. A monotone and the bright tone were used. The second, and the season different difference, the out line stitch, an applique, and the cut work technique S/S season were a feature. A plant, and the animal motive were expressed as the front arrangement and the monotone of the achromatic color appeared. As to F/W season, the long short stitch and satin stitch techniques were with the characteristic profit. The abstract motive showed up as the edge alignment and composite arrangement. And the plain tone and the monotone of the chromatics combination color are used. In the third, and the chronological difference, an applique the embroidery technique showed up in the out line stitch, and 2007 years in 2004 years and 2006 years. And the sentence motive of the animal, and the abstract motive the embroidery motive are embossed in 2005 years and 2006 years in 2008 years.