• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3230-3255
• /
• 2022

Causality mining in NLP is a significant area of interest, which benefits in many daily life applications, including decision making, business risk management, question answering, future event prediction, scenario generation, and information retrieval. Mining those causalities was a challenging and open problem for the prior non-statistical and statistical techniques using web sources that required hand-crafted linguistics patterns for feature engineering, which were subject to domain knowledge and required much human effort. Those studies overlooked implicit, ambiguous, and heterogeneous causality and focused on explicit causality mining. In contrast to statistical and non-statistical approaches, we present Bidirectional Encoder Representations from Transformers (BERT) integrated with Multi-level Feature Networks (MFN) for causality recognition, called BERT+MFN for causality recognition in noisy and informal web datasets without human-designed features. In our model, MFN consists of a three-column knowledge-oriented network (TC-KN), bi-LSTM, and Relation Network (RN) that mine causality information at the segment level. BERT captures semantic features at the word level. We perform experiments on Alternative Lexicalization (AltLexes) datasets. The experimental outcomes show that our model outperforms baseline causality and text mining techniques.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.706-708
• /
• 2023

In this study, we embark on a journey to uncover the essence of emotions by exploring the depths of transfer learning on three pre-trained transformer models. Our quest to classify five emotions culminates in discovering the KLUE (Korean Language Understanding Evaluation)-BERT (Bidirectional Encoder Representations from Transformers) model, which is the most exceptional among its peers. Our analysis of F1 scores attests to its superior learning and generalization abilities on the experimental data. To delve deeper into the mystery behind its success, we employ the powerful SHAP (Shapley Additive Explanations) method to unravel the intricacies of the KLUE-BERT model. The findings of our investigation are presented with a mesmerizing text plot visualization, which serves as a window into the model's soul. This approach enables us to grasp the impact of individual tokens on emotion classification and provides irrefutable, visually appealing evidence to support the predictions of the KLUE-BERT model.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.344-358
• /
• 2022

Text summarization is the task of producing a shorter version of a long document while accurately preserving the main contents of the original text. Abstractive summarization generates novel words and phrases using a language generation method through text transformation and prior-embedded word information. However, newly coined words or out-of-vocabulary words decrease the performance of automatic summarization because they are not pre-trained in the machine learning process. In this study, we demonstrated an improvement in summarization quality through the contextualized embedding of BERT with out-of-vocabulary masking. In addition, explicitly providing precise pointing and an optional copy instruction along with BERT embedding, we achieved an increased accuracy than the baseline model. The recall-based word-generation metric ROUGE-1 score was 55.11 and the word-order-based ROUGE-L score was 39.65.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.237-240
• /
• 2020

사전학습 언어모델은 다양한 자연어처리 작업에서 높은 성능을 보였다. 하지만, 사전학습 언어모델은 문장 내 문맥 정보만을 학습하기 때문에 단어간 의미관계 정보를 추론하는데는 한계가 있다. 최근에는, 사전학습 언어모델이 어느수준으로 단어간 의미관계를 이해하고 있는지 다양한 Probing Test를 진행하고 있다. 이러한 Test는 언어모델의 강점과 약점을 분석하는데 효율적이며, 한층 더 인간의 언어를 정확하게 이해하기 위한 모델을 구축하는데 새로운 방향을 제시한다. 본 논문에서는 대표적인 사전 학습기반 언어모델인 BERT(Bidirectional Encoder Representations from Transformers)의 단어간 의미관계 이해도를 평가하는 3가지 작업을 진행한다. 첫 번째로 단어 간의 상위어, 하위어 관계를 나타내는 IsA 관계를 분석한다. 두번째는 '자동차'와 '변속'과 같은 관계를 나타내는 PartOf 관계를 분석한다. 마지막으로 '새'와 '날개'와 같은 관계를 나타내는 HasA 관계를 분석한다. 결과적으로, BERT_base 모델에 대해서는 추론 결과 대부분에서 낮은 성능을 보이지만, BERT_large 모델에서는 BERT_base보다 높은 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.167-171
• /
• 2020

문서 요약은 길이가 긴 원본 문서에서 의미를 유지한 채 짧은 문서나 문장을 얻어내는 작업을 의미한다. 딥러닝을 이용한 자연어처리 기술들이 연구됨에 따라 end-to-end 방식의 자연어 생성 모델인 sequence-to-sequence 모델을 문서 요약 생성에 적용하는 방법들이 연구되었다. 본 논문에서는 여러 자연어처리 분야에서 높은 성능을 보이고 있는 BERT 모델을 이용한 자연어 생성 모델에 복사 메커니즘과 강화 학습을 추가한 문서 요약 모델을 제안한다. 복사 메커니즘은 입력 문장의 단어들을 출력 문장에 복사하는 기술로 학습데이터에서 학습되기 힘든 고유 명사 등의 단어들에 대한 성능을 높이는 방법이다. 강화 학습은 정답 단어의 확률을 높이기 위해 학습하는 지도 학습 방법과는 달리 연속적인 단어 생성으로 얻어진 전체 문장의 보상 점수를 높이는 방향으로 학습하여 생성되는 단어 자체보다는 최종 생성된 문장이 더 중요한 자연어 생성 문제에 효과적일 수 있다. 실험결과 기존의 BERT 생성 모델 보다 복사 메커니즘과 강화 학습을 적용한 모델의 Rouge score가 더 높음을 확인 하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.617-623
• /
• 2024

Identifying emotions through speech poses a significant challenge due to the complex relationship between language and emotions. Our paper aims to take on this challenge by employing feature engineering to identify emotions in speech through a multimodal classification task involving both speech and text data. We evaluated two classifiers-Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM)-both integrated with a BERT-based pre-trained model. Our assessment covers various performance metrics (accuracy, F-score, precision, and recall) across different experimental setups). The findings highlight the impressive proficiency of two models in accurately discerning emotions from both text and speech data.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.55-62
• /
• 2022

A smart tourism chatbot is needed as a user interface to efficiently provide smart tourism services such as recommended travel products, tourist information, my travel itinerary, and tour guide service to tourists. We have been developed a smart tourism app and a smart tourism information system that provide smart tourism services to tourists. We also developed a smart tourism chatbot service consisting of khaiii morpheme analyzer, rule-based intention classification, and tourism information knowledge base using Neo4j graph database. In this paper, we develop the Korean and English smart tourism Name Entity (NE) datasets required for the development of the NER model using the pre-trained language models (PLMs) for the smart tourism chatbot system. We create the tourism information NER datasets by collecting source data through smart tourism app, visitJeju web of Jeju Tourism Organization (JTO), and web search, and preprocessing it using Korean and English tourism information Name Entity dictionaries. We perform training on the KoBERT-CRF NER model using the developed Korean and English tourism information NER datasets. The weight-averaged precision, recall, and f1 scores are 0.94, 0.92 and 0.94 on Korean and English tourism information NER datasets.

• Journal of the Korean Society for information Management
• /
• v.38 no.2
• /
• pp.153-172
• /
• 2021

This study is to create a deep learning based classification model to examine the characteristics of panic disorder and to classify the panic disorder tendency literature by the panic disorder corpus constructed for the present study. For this purpose, 5,884 documents of the panic disorder corpus collected from social media were directly annotated based on the mental disease diagnosis manual and were classified into panic disorder-prone and non-panic-disorder documents. Then, TF-IDF scores were calculated and word co-occurrence analysis was performed to analyze the lexical characteristics of the corpus. In addition, the co-occurrence between the symptom frequency measurement and the annotated symptom was calculated to analyze the characteristics of panic disorder symptoms and the relationship between symptoms. We also conducted the performance evaluation for a deep learning based classification model. Three pre-trained models, BERT multi-lingual, KoBERT, and KcBERT, were adopted for classification model, and KcBERT showed the best performance among them. This study demonstrated that it can help early diagnosis and treatment of people suffering from related symptoms by examining the characteristics of panic disorder and expand the field of mental illness research to social media.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.624-626
• /
• 2023

Credit scoring is a technique used by financial institutions to assess the creditworthiness of potential borrowers. This involves evaluating a borrower's credit history to predict the likelihood of defaulting on a loan. This paper presents an ensemble of two Transformer based models within a framework for discriminating the default risk of loan applications in the field of credit scoring. The first model is FinBERT, a pretrained NLP model to analyze sentiment of financial text. The second model is FT-Transformer, a simple adaptation of the Transformer architecture for the tabular domain. Both models are trained on the same underlying data set, with the only difference being the representation of the data. This multi-modal approach allows us to leverage the unique capabilities of each model and potentially uncover insights that may not be apparent when using a single model alone. We compare our model with two famous ensemble-based models, Random Forest and Extreme Gradient Boosting.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3211-3229
• /
• 2022

To solve the problems existing in the process of Weibo disaster rumor recognition, such as lack of corpus, poor text standardization, difficult to learn semantic information, and simple semantic features of disaster rumor text, this paper takes Sina Weibo as the data source, constructs a dataset for Weibo disaster rumor recognition, and proposes a deep learning model BERT_AT_Stacked LSTM for Weibo disaster rumor recognition. First, add adversarial disturbance to the embedding vector of each word to generate adversarial samples to enhance the features of rumor text, and carry out adversarial training to solve the problem that the text features of disaster rumors are relatively single. Second, the BERT part obtains the word-level semantic information of each Weibo text and generates a hidden vector containing sentence-level feature information. Finally, the hidden complex semantic information of poorly-regulated Weibo texts is learned using a Stacked Long Short-Term Memory (Stacked LSTM) structure. The experimental results show that, compared with other comparative models, the model in this paper has more advantages in recognizing disaster rumors on Weibo, with an F1_Socre of 97.48%, and has been tested on an open general domain dataset, with an F1_Score of 94.59%, indicating that the model has better generalization.