• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.39-46
• /
• 2022

In this paper, we propose a multi-task model that can simultaneously predict general-purpose tasks such as part-of-speech tagging, lemmatization, and dependency parsing using the UD Korean Kaist v2.3 corpus. The proposed model thus applies the self-attention technique of the BERT model and the graph-based Biaffine attention technique by fine-tuning the multilingual BERT and the two Korean-specific BERTs such as KR-BERT and KoBERT. The performances of the proposed model are compared and analyzed using the multilingual version of BERT and the two Korean-specific BERT language models.

• Knowledge Management Research
• /
• v.22 no.3
• /
• pp.91-106
• /
• 2021

With the recent rapid development of deep learning technology, the demand for analyzing huge text documents in the national R&D field from various perspectives is rapidly increasing. In particular, interest in the application of a BERT(Bidirectional Encoder Representations from Transformers) language model that has pre-trained a large corpus is growing. However, the terminology used frequently in highly specialized fields such as national R&D are often not sufficiently learned in basic BERT. This is pointed out as a limitation of understanding documents in specialized fields through BERT. Therefore, this study proposes a method to build an R&D KoBERT language model that transfers national R&D field knowledge to basic BERT using further pre-training. In addition, in order to evaluate the performance of the proposed model, we performed classification analysis on about 116,000 R&D reports in the health care and information and communication fields. Experimental results showed that our proposed model showed higher performance in terms of accuracy compared to the pure KoBERT model.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.148-155
• /
• 2024

Despite the increasing importance of irony and sarcasm detection in the field of natural language processing, research on the Korean language is relatively scarce compared to other languages. This study aims to experiment with various models for irony detection in Korean text. The study conducted irony detection experiments using KoBERT, a BERT-based model, and ChatGPT. For KoBERT, two methods of additional training on sentiment data were applied (Transfer Learning and MultiTask Learning). Additionally, for ChatGPT, the Few-Shot Learning technique was applied by increasing the number of example sentences entered as prompts. The results of the experiments showed that the Transfer Learning and MultiTask Learning models, which were trained with additional sentiment data, outperformed the baseline model without additional sentiment data. On the other hand, ChatGPT exhibited significantly lower performance compared to KoBERT, and increasing the number of example sentences did not lead to a noticeable improvement in performance. In conclusion, this study suggests that a model based on KoBERT is more suitable for irony detection than ChatGPT, and it highlights the potential contribution of additional training on sentiment data to improve irony detection performance.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.340-345
• /
• 2021

최근 많은 연구들이 BERT를 활용하여, 주어진 문맥에서 언어학/문법적으로 적절하지 않은 단어를 인지하고 찾아내는 성과를 보고하였다. 하지만 일반적으로 딥러닝 관점에서 NLL기법(Negative log-likelihood)은 주어진 문맥에서 언어 변칙에 대한 정확한 성격을 규명하기에는 어려움이 있다고 지적되고 있다. 이러한 한계를 해결하기 위하여, Li et al.(2021)은 트랜스포머 언어모델의 은닉층별 밀도 추정(density estimation)을 통한 가우시안 확률 분포를 활용하는 가우시안 혼합 모델(Gaussian Mixture Model)을 적용하였다. 그들은 트랜스포머 언어모델이 언어 변칙 예문들의 종류에 따라 상이한 메커니즘을 사용하여 처리한다는 점을 보고하였다. 이 선행 연구를 받아들여 본 연구에서는 한국어 기반 언어모델인 KoBERT나 KR-BERT도 과연 한국어의 상이한 유형의 언어 변칙 예문들을 다른 방식으로 처리할 수 있는지를 규명하고자 한다. 이를 위해, 본 연구에서는 한국어 형태통사적 그리고 의미적 변칙 예문들을 구성하였고, 이 예문들을 바탕으로 한국어 기반 모델들의 성능을 놀라움-갭(surprisal gap) 점수를 계산하여 평가하였다. 본 논문에서는 한국어 기반 모델들도 의미적 변칙 예문을 처리할 때보다 형태통사적 변칙 예문을 처리할 때 상대적으로 보다 더 높은 놀라움-갭 점수를 보여주고 있음을 발견하였다. 즉, 상이한 종류의 언어 변칙 예문들을 처리하기 위하여 다른 메커니즘을 활용하고 있음을 보였다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.1-9
• /
• 2021

Disaster alerts are text messages sent by government to people in the area in the event of a disaster. Since the number of disaster alerts has increased, the number of people who block disaster alerts is increasing as many unnecessary disaster alerts are being received. To solve this problem, this study proposes a deep learning model that automatically classifies disaster alerts by disaster type, and allows only necessary disaster alerts to be received according to the recipient. The proposed model embeds disaster alerts via KoBERT and classifies them by disaster type with LSTM. As a result of classifying disaster alerts using 3 combinations of parts of speech: [Noun], [Noun + Adjective + Verb] and [All parts], and 4 classification models: Proposed model, Keyword classification, Word2Vec + 1D-CNN and KoBERT + FFNN, the proposed model achieved the highest performance with 0.988954 accuracy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.975-977
• /
• 2020

감정 분석은 문서의 주관적인 감정, 의견, 기분을 파악하기 위한 방법으로 소셜 미디어, 온라인 리뷰 등 다양한 분야에서 활용된다. 문서 내 텍스트가 나타내는 단어와 문맥을 기반으로 감정 수치를 계산하여 긍정 또는 부정 감정을 결정한다. 2015년에 구축된 네이버 영화평 데이터 20 만개에 12 만개를 추가 구축하여 감정 분석 연구를 진행하였으며 언어 모델로는 최근 자연어처리 분야에서 높은 성능을 보여주는 BERT 모델을 이용하였다. 감정 분석 기법으로는 LSTM(Long Short-Term Memory) 등 기존의 기계학습 기법과 구글의 다국어 BERT 모델, 그리고 KoBERT 모델을 이용하여 감정 분석의 성능을 비교하였으며, KoBERT 모델이 89.90%로 가장 높은 성능을 보여주었다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.437-446
• /
• 2022

Text classification task from Natural Language Processing (NLP) combined with state-of-the-art (SOTA) Machine Learning (ML) and Deep Learning (DL) algorithms as the core engine is widely used to detect and classify voice phishing call transcripts. While numerous studies on the classification of voice phishing call transcripts are being conducted and demonstrated good performances, with the increase of non-face-to-face financial transactions, there is still the need for improvement using the latest NLP technologies. This paper conducts a benchmarking of Korean voice phishing detection performances of the pre-trained Korean language model KoBERT, against multiple other SOTA algorithms based on the classification of related transcripts from the labeled Korean voice phishing dataset called KorCCVi. The results of the experiments reveal that the classification accuracy on a test set of the KoBERT model outperforms the performances of all other models with an accuracy score of 99.60%.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.133-140
• /
• 2022

We investigate the performance of deep learning-based Korean language models on a task of predicting the score range of Korean essays written by foreign students. We construct a data set containing a total of 304 essays, which include essays discussing the criteria for choosing a job ('job'), conditions of a happy life ('happ'), relationship between money and happiness ('econ'), and definition of success ('succ'). These essays were labeled according to four letter grades (A, B, C, and D), and a total of eleven essay score range prediction experiments were conducted (i.e., five for predicting the score range of 'job' essays, five for predicting the score range of 'happiness' essays, and one for predicting the score range of mixed topic essays). Three deep learning-based Korean language models, KoBERT, KcBERT, and KR-BERT, were fine-tuned using various training data. Moreover, two traditional probabilistic machine learning classifiers, naive Bayes and logistic regression, were also evaluated. Experiment results show that deep learning-based Korean language models performed better than the two traditional classifiers, with KR-BERT performing the best with 55.83% overall average prediction accuracy. A close second was KcBERT (55.77%) followed by KoBERT (54.91%). The performances of naive Bayes and logistic regression classifiers were 52.52% and 50.28% respectively. Due to the scarcity of training data and the imbalance in class distribution, the overall prediction performance was not high for all classifiers. Moreover, the classifiers' vocabulary did not explicitly capture the error features that were helpful in correctly grading the Korean essay. By overcoming these two limitations, we expect the score range prediction performance to improve.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.149-152
• /
• 2019

감성분석이란 입력된 텍스트의 감성을 분류하는 자연어처리의 한 분야로, 최근 CNN, RNN, Transformer등의 딥러닝 기법을 적용한 다양한 연구가 있다. 한국어 감성분석을 진행하기 위해서는 형태소, 음절 등의 추가 자질을 활용하는 것이 효과적이며 성능 향상을 기대할 수 있는 방법이다. 모델 생성에 있어서 아키텍쳐 구성도 중요하지만 문맥에 따른 언어를 컴퓨터가 표현할 수 있는 지식 표현 체계 구성도 상당히 중요하다. 이러한 맥락에서 BERT모델은 문맥을 완전한 양방향으로 이해할 수있는 Language Representation 기반 모델이다. 본 논문에서는 최근 CNN, RNN이 융합된 모델과 Transformer 기반의 한국어 KoBERT 모델에 대해 감성분석 task에서 다양한 성능비교를 진행했다. 성능분석 결과 어절단위 한국어 KoBERT모델에서 90.50%의 성능을 보여주었다.

• 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.