• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.771-789
• /
• 2019

Text detection has been a popular research topic in the field of computer vision. It is difficult for prevalent text detection algorithms to avoid the dependence on datasets. To overcome this problem, we proposed a novel unsupervised text detection algorithm inspired by bootstrap learning. Firstly, the text candidate in a novel form of superpixel is proposed to improve the text recall rate by image segmentation. Secondly, we propose a unique text sample selection model (TSSM) to extract text samples from the current image and eliminate database dependency. Specifically, to improve the precision of samples, we combine maximally stable extremal regions (MSERs) and the saliency map to generate sample reference maps with a double threshold scheme. Finally, a multiple kernel boosting method is developed to generate a strong text classifier by combining multiple single kernel SVMs based on the samples selected from TSSM. Experimental results on standard datasets demonstrate that our text detection method is robust to complex backgrounds and multilingual text and shows stable performance on different standard datasets.

• International Journal of Advanced Culture Technology
• /
• 제9권2호
• /
• pp.86-90
• /
• 2021

Sentiment refers to a person's thoughts, opinions, and feelings toward an object. Sentiment analysis is a process of collecting opinions on a specific target and classifying them according to their emotions, and applies to opinion mining that analyzes product reviews and reviews on the web. Companies and users can grasp the opinions of public opinion and come up with a way to do so. Recently, natural language processing models using the Transformer structure have appeared, and Google's BERT is a representative example. Afterwards, various models came out by remodeling the BERT. Among them, the Facebook AI team unveiled the XLM-R (XLM-RoBERTa), an upgraded XLM model. XLM-R solved the data limitation and the curse of multilinguality by training XLM with 2TB or more refined CC (CommonCrawl), not Wikipedia data. This model showed that the multilingual model has similar performance to the single language model when it is trained by adjusting the size of the model and the data required for training. Therefore, in this paper, we study the improvement of Korean sentiment analysis performed using a pre-trained XLM-R model that solved curse of multilinguality and improved performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권4호
• /
• pp.1166-1186
• /
• 2022

Artistic font design has become an integral part of visual media. However, without prior knowledge of the font domain, it is difficult to create distinct font styles. When the number of characters is limited, this task becomes easier (e.g., only Latin characters). However, designing CJK (Chinese, Japanese, and Korean) characters presents a challenge due to the large number of character sets and complexity of the glyph components in these languages. Numerous studies have been conducted on automating the font design process using generative adversarial networks (GANs). Existing methods rely heavily on reference fonts and perform font style conversions between different fonts. Additionally, rather than capturing style information for a target font via multiple style images, most methods do so via a single font image. In this paper, we propose a network architecture for generating multilingual font sets that makes use of geometric structures as content. Additionally, to acquire sufficient style information, we employ multiple style images belonging to a single font style simultaneously to extract global font style-specific information. By utilizing the geometric structural information of content and a few stylized images, our model can generate an entire font set while maintaining the style. Extensive experiments were conducted to demonstrate the proposed model's superiority over several baseline methods. Additionally, we conducted ablation studies to validate our proposed network architecture.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.223-229
• /
• 2022

LinkedIn is one of the most job hunting and career-growing applications in the world. There are a lot of opportunities and jobs available on LinkedIn. According to statistics, LinkedIn has 738M+ members. 14M+ open jobs on LinkedIn and 55M+ Companies listed on this mega-connected application. A lot of vacancies are available daily. LinkedIn data has been used for the research work carried out in this paper. This in turn can significantly tackle the challenges faced by LinkedIn and other job posting applications to improve the levels of jobs available in the industry. This research introduces Text Processing in natural language processing on datasets of LinkedIn which aims to find out the jobs that appear most in a month or/and year. Therefore, the large data became renewed into the required or needful source. This study thus uses Multinomial Naïve Bayes and Linear Support Vector Machine learning algorithms for text classification and developed a trained multilingual dataset. The results indicate the most needed job vacancies in any field. This will help students, job seekers, and entrepreneurs with their career decisions

• Journal of Information Science Theory and Practice
• /
• 제11권1호
• /
• pp.61-78
• /
• 2023

Ontological knowledge modelling of epic texts, though being an established research arena backed by concrete multilingual and multicultural works, still suffers from two key shortcomings. Firstly, all epic ontological models developed till date have been designed following ad-hoc methodologies, most often combining existing general purpose ontology development methodologies. Secondly, none of the ad-hoc methodologies consider the potential reuse of existing epic ontological models for enrichment, if available. This paper presents, as a unified solution to the above shortcomings, the design and development of GOMME - the first dedicated methodology for iterative ontological modelling of epics, potentially extensible to works in different research arenas of digital humanities in general. GOMME is grounded in transdisciplinary foundations of canonical norms for epics, knowledge modelling best practices, application satisfiability norms, and cognitive generative questions. It is also the first methodology (in epic modelling but also in general) to be flexible enough to integrate, in practice, the options of knowledge modelling via reuse or from scratch. The feasibility of GOMME is validated via a first brief implementation of ontological modelling of the Indian epic Mahabharata by reusing an existing ontology. The preliminary results are promising, with the GOMME-produced model being both ontologically thorough and competent performance-wise.

• 한국환경보건학회지
• /
• 제49권4호
• /
• pp.201-209
• /
• 2023

Background: To describe domain knowledge consistently and precisely, the establishment of a controlled vocabulary, a so-called ontology, is essential. Internationally, the plant ontology (PO) in the ecology field has been developed for the anatomy and developmental stages of plants in English, Spanish, and Japanese, but there is no Korean version of the PO due to a lack of knowledge on standardization for Korean plants. Objectives: We aimed to establish a Korean plant ontology with core PO architectures. Methods: The latest ontology web language (OWL)-formatted raw version of the PO was collected from the PO consortium site. A formal workflow process and OWL file-handing tools for efficient Korean content development were conducted and executed. Results: The macro- and micro-perspective frameworks of the PO were presented by analyzing the upper model and the internal OWL-leveled physical structure, respectively. We developed and validated Korean knowledge content for a total of 1,957 classes included in the PO and transplanted them into an ontology modeling system. Conclusions: A Korean plant ontology was established for international harmonization through improved compatibility and data exchangeability with multilingual environmental and ecological knowledge bases.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.9-15
• /
• 2021

기계번역 품질 예측 (Quality Estimation, QE)은 정답 문장에 대한 참조없이 소스 문장과 기계번역 결과를 통해 기계번역 결과에 대한 품질을 수준별 주석으로 나타내주는 태스크이며, 다양한 활용도가 있다는 점에서 꾸준히 연구가 수행되고 있다. 그러나 QE 모델 학습을 위한 데이터 구성 시 기계번역 결과에 대해 번역 전문가가 교정한 문장이 필요한데, 이를 제작하는 과정에서 상당한 인건비와 시간 비용이 발생하는 한계가 있다. 본 논문에서는 번역 전문가 없이 병렬 또는 단일 말뭉치와 기계번역기만을 활용하여 자동화된 방식으로 한국어-영어 합성 QE 데이터를 구축하며, 최초로 단어 수준의 한국어-영어 기계번역 결과 품질 예측 모델을 제작하였다. QE 모델 제작 시에는 Cross-lingual language model (XLM), XLM-RoBERTa (XLM-R), multilingual BART (mBART)와 같은 다언어모델들을 활용하여 비교 실험을 수행했다. 또한 기계번역 결과에 대한 품질 예측의 객관성을 검증하고자 구글, 아마존, 마이크로소프트, 시스트란의 번역기를 활용하여 모델 평가를 진행했다. 실험 결과 XLM-R을 활용하여 미세조정학습한 QE 모델이 가장 좋은 성능을 보였으며, 품질 예측의 객관성을 확보함으로써 QE의 다양한 장점들을 한국어-영어 기계번역에서도 활용할 수 있도록 했다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.414-418
• /
• 2021

다국어 음성인식은 단일언어 음성인식에 비해 높은 난이도를 보인다. 하나의 단일 모델로 다국어 음성인식을 수행하기 위해선 다양한 언어가 공유하는 음성적 특성을 모델이 학습할 수 있도록 하여 음성인식 성능을 향상시킬 수 있다. 본 연구는 딥러닝 음성인식 모델인 Wav2Vec2.0 구조를 변경하여 한국어와 영어 음성을 하나의 모델로 학습하는 방법을 제시한다. CTC(Connectionist Temporal Classification) 손실함수를 이용하는 Wav2Vec2.0 모델의 구조에서 각 언어마다 별도의 CTC 출력 계층을 두고 각 언어별 사전(Lexicon)을 적용하여 음성 입력을 다른 언어로 혼동되는 경우를 원천적으로 방지한다. 제시한 Wav2Vec2.0 구조를 사용하여 한국어와 영어를 잘못 분류하여 음성인식률이 낮아지는 문제를 해결하고 더불어 제시된 한국어 음성 데이터셋(KsponSpeech)에서 한국어와 영어를 동시에 학습한 모델이 한국어만을 이용한 모델보다 향상된 음성 인식률을 보임을 확인하였다. 마지막으로 Prefix 디코딩을 활용하여 언어모델을 이용한 음성인식 성능 개선을 수행하였다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.161-166
• /
• 2021

본 연구는 한국어 문장 임베딩(embedding)에 담겨진 언어적 속성을 평가하기 위한 프로빙 태스크(Probing Task)를 소개한다. 프로빙 태스크는 임베딩으로부터 문장의 표층적, 통사적, 의미적 속성을 구분하는 문제로 영어, 폴란드어, 러시아어 문장에 적용된 프로빙 테스크를 소개하고, 이를 기반으로하여 한국어 문장의 속성을 잘 보여주는 한국어 문장 임베딩 프로빙 태스크를 설계하였다. 언어 공통적으로 적용 가능한 6개의 프로빙 태스크와 한국어 문장의 주요 특징인 주어 생략(SubjOmission), 부정법(Negation), 경어법(Honorifics)을 추가로 고안하여 총 9개의 프로빙 태스크를 구성하였다. 각 태스크를 위한 데이터셋은 '세종 구문분석 말뭉치'를 의존구문문법(Universal Dependency Grammar) 구조로 변환한 후 자동으로 구축하였다. HuggingFace에 공개된 4개의 다국어(multilingual) 문장 인코더와 4개의 한국어 문장 인코더로부터 획득한 임베딩의 언어적 속성을 프로빙 태스크를 통해 비교 분석한 결과, 다국어 문장 인코더인 mBART가 9개의 프로빙 태스크에서 전반적으로 높은 성능을 보였다. 또한 한국어 문장 임베딩에는 표층적, 통사적 속성보다는 심층적인 의미적 속성을 더욱 잘 담고 있음을 확인할 수 있었다.