• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.263-283
• /
• 2024

Users' comments after online shopping are critical to product reputation and business improvement. These comments, sometimes known as e-commerce reviews, influence other customers' purchasing decisions. To confront large amounts of e-commerce reviews, automatic analysis based on machine learning and deep learning draws more and more attention. A core task therein is sentiment analysis. However, the e-commerce reviews exhibit the following characteristics: (1) inconsistency between comment content and the star rating; (2) a large number of unlabeled data, i.e., comments without a star rating, and (3) the data imbalance caused by the sparse negative comments. This paper employs Bidirectional Encoder Representation from Transformers (BERT), one of the best natural language processing models, as the base model. According to the above data characteristics, we propose the F_MixBERT framework, to more effectively use inconsistently low-quality and unlabeled data and resolve the problem of data imbalance. In the framework, the proposed MixBERT incorporates the MixMatch approach into BERT's high-dimensional vectors to train the unlabeled and low-quality data with generated pseudo labels. Meanwhile, data imbalance is resolved by Focal loss, which penalizes the contribution of large-scale data and easily-identifiable data to total loss. Comparative experiments demonstrate that the proposed framework outperforms BERT and MixBERT for sentiment analysis of e-commerce comments.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.299-312
• /
• 2021

It is necessary to achieve high performance in the task of zero anaphora resolution (ZAR) for completely understanding the texts in Korean, Japanese, Chinese, and various other languages. Deep-learning-based models are being employed for building ZAR systems, owing to the success of deep learning in the recent years. However, the objective of building a high-quality ZAR system is far from being achieved even using these models. To enhance the current ZAR techniques, we fine-tuned a pretrained bidirectional encoder representations from transformers (BERT). Notably, BERT is a general language representation model that enables systems to utilize deep bidirectional contextual information in a natural language text. It extensively exploits the attention mechanism based upon the sequence-transduction model Transformer. In our model, classification is simultaneously performed for all the words in the input word sequence to decide whether each word can be an antecedent. We seek end-to-end learning by disallowing any use of hand-crafted or dependency-parsing features. Experimental results show that compared with other models, our approach can significantly improve the performance of ZAR.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.29-35
• /
• 2020

In this paper, we propose a new structured entity recognition DeNERT model. Recently, the field of natural language processing has been actively researched using pre-trained language representation models with a large amount of corpus. In particular, the named entity recognition, which is one of the fields of natural language processing, uses a supervised learning method, which requires a large amount of training dataset and computation. Reinforcement learning is a method that learns through trial and error experience without initial data and is closer to the process of human learning than other machine learning methodologies and is not much applied to the field of natural language processing yet. It is often used in simulation environments such as Atari games and AlphaGo. BERT is a general-purpose language model developed by Google that is pre-trained on large corpus and computational quantities. Recently, it is a language model that shows high performance in the field of natural language processing research and shows high accuracy in many downstream tasks of natural language processing. In this paper, we propose a new named entity recognition DeNERT model using two deep learning models, DQN and BERT. The proposed model is trained by creating a learning environment of reinforcement learning model based on language expression which is the advantage of the general language model. The DeNERT model trained in this way is a faster inference time and higher performance model with a small amount of training dataset. Also, we validate the performance of our model's named entity recognition performance through experiments.

• The Journal of Society for e-Business Studies
• /
• v.25 no.1
• /
• pp.203-214
• /
• 2020

It is necessary to classify technical documents such as patents, R&D project reports in order to understand the trends of technology convergence and interdisciplinary joint research, technology development and so on. Text mining techniques have been mainly used to classify these technical documents. However, in the case of classifying technical documents by text mining algorithms, there is a disadvantage that the features representing technical documents must be directly extracted. In this study, we propose a BERT-based document classification model to automatically extract document features from text information of national R&D projects and to classify them. Then, we verify the applicability and performance of the proposed model for classifying documents.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.157-165
• /
• 2021

Recently, studies using deep learning to analyze a large amount of text are being actively conducted. In particular, a pre-trained language model that applies the learning results of a large amount of text to the analysis of a specific domain text is attracting attention. Among various pre-trained language models, BERT(Bidirectional Encoder Representations from Transformers)-based model is the most widely used. Recently, research to improve the performance of analysis is being conducted through further pre-training using BERT's MLM(Masked Language Model). However, the traditional MLM has difficulties in clearly understands the meaning of sentences containing new words such as newly coined words. Therefore, in this study, we newly propose NTM(Newly coined words Target Masking), which performs masking only on new words. As a result of analyzing about 700,000 movie reviews of portal 'N' by applying the proposed methodology, it was confirmed that the proposed NTM showed superior performance in terms of accuracy of sensitivity analysis compared to the existing random masking.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.57-66
• /
• 2022

In this paper, we propose a legal document search method that uses the Sentence-BERT model. The general public who wants to use the legal search service has difficulty searching for relevant precedents due to a lack of understanding of legal terms and structures. In addition, the existing keyword and text mining-based legal search methods have their limits in yielding quality search results for two reasons: they lack information on the context of the judgment, and they fail to discern homonyms and polysemies. As a result, the accuracy of the legal document search results is often unsatisfactory or skeptical. To this end, This paper aims to improve the efficacy of the general public's legal search in the Supreme Court precedent and Legal Aid Counseling case database. The Sentence-BERT model embeds contextual information on precedents and counseling data, which better preserves the integrity of relevant meaning in phrases or sentences. Our initial research has shown that the Sentence-BERT search method yields higher accuracy than the Doc2Vec or TF-IDF search methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.810-813
• /
• 2020

자연어처리 분야에서 딥러닝 기반의 분류 모델은 획기적인 성능을 보여주고 있다. 특히 2018 년 발표된 구글의 BERT 는 다양한 태스크에서 높은 성능을 보여준다. 본 논문에서는 이러한 BERT 가 클래스 불균형이 심한 데이터에 대해 어느 정도 성능을 보여주는지 확인하고 이를 해결하는 방법으로 EDA 를 선택해 성능을 개선하고자 한다. BERT 에 알맞게 적용하기 위해 다양한 방법으로 EDA 를 구현했고 이에 대한 성능을 평가하였다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.465-469
• /
• 2019

자연어 처리를 위해서 두 문장의 의미 유사성을 분석하는 것은 아주 중요하다. 이 논문은 패러프레이즈 검출 태스크를 수행하기 위한 Paraphrase-BERT를 제안한다. 우선 구글이 제안한 사전 학습된 BERT를 그대로 이용해서 패러프레이즈 데이터 (MRPC)를 가지고 파인 튜닝하였고 추가적으로 최근에 구글에서 새로 발표한 Whole Word Masking 기술을 사용하여 사전 학습된 BERT 모델을 새롭게 파인 튜닝하였다. 그리고 마지막으로 다중 작업 학습을 수행하여 성능을 향상시켰다. 구체적으로 질의 응답 태스크와 패러프레이즈 검출 태스크를 동시에 학습하여 후자가 더 잘 수행될 수 있도록 하였다. 결과적으로 점점 더 성능이 개선되었고 (11.11%의 정확도 향상, 7.88%의 F1 점수 향상), 향후 작업으로 파인 튜닝하는 방법에 대해서 추가적으로 연구할 계획이다.