• ETRI Journal
• /
• 제43권2호
• /
• 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.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.652-657
• /
• 2018

With the rapid development of e-commerce, many customers can now express their opinion on various kinds of product at discussion groups, merchant sites, social networks, etc. Discerning a consensus opinion about a product sold online is difficult due to more and more reviews become available on the internet. Opinion Mining, also known as Sentiment analysis, is the task of automatically detecting and understanding the sentimental expressions about a product from customer textual reviews. Recently, researchers have proposed various approaches for evaluation in sentiment mining by applying several techniques for document, sentence and aspect level. Aspect-based sentiment analysis is getting widely interesting of researchers; however, more complex algorithms are needed to address this issue precisely with larger corpora. This paper introduces an approach of knowledge representation for the task of analyzing product aspect rating. We focus on how to form the nature of sentiment representation from textual opinion by utilizing the representation learning methods which include word embedding and compositional vector models. Our experiment is performed on a dataset of reviews from electronic domain and the obtained result show that the proposed system achieved outstanding methods in previous studies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3804-3819
• /
• 2018

The increasing popularity of HTTP adaptive video streaming services has dramatically increased bandwidth requirements on operator networks, which attempt to shape their traffic through Deep Packet inspection (DPI). However, Google and certain content providers have started to encrypt their video services. As a result, operators often encounter difficulties in shaping their encrypted video traffic via DPI. This highlights the need for new traffic classification methods for encrypted HTTP adaptive video streaming to enable smart traffic shaping. These new methods will have to effectively estimate the quality representation layer and playout buffer. We present a new machine learning method and show for the first time that video quality representation classification for (YouTube) encrypted HTTP adaptive streaming is possible. The crawler codes and the datasets are provided in [43,44,51]. An extensive empirical evaluation shows that our method is able to independently classify every video segment into one of the quality representation layers with 97% accuracy if the browser is Safari with a Flash Player and 77% accuracy if the browser is Chrome, Explorer, Firefox or Safari with an HTML5 player.

• 대한기계학회논문집A
• /
• 제20권4호
• /
• pp.2752-2759
• /
• 1996

This paper presents crack growth analysis approach on the basis of neural networks, a branch of cognitive science to high temperature low cycle fatigue that shows strong nonlinearity in material behavior. As the number of data patterns on crack growth increase, pattern classification occurs well and two point representation scheme with gradient of crack growth curve simulates crack growth rate better than one point representation scheme. Optimal number of learning data exists and excessive number of learning data increases estimated mean error with remarkable learning time J-da/dt relation predicted by neural networks shows that test condition with unlearned data is simulated well within estimated mean error(5%).

• 정보과학회 논문지
• /
• 제45권1호
• /
• pp.15-21
• /
• 2018

낮은 계수 표현(Low-Rank Representation, LRR) 기반 방법은 얼굴 클러스터링, 객체 검출 등의 여러 실제 응용에 널리 사용되고 있다. 이 방법은 그래프 기반 준지도 학습에서 그래프 구축에 사용할 경우 높은 예측 정확도를 확보할 수 있어 많이 사용된다. 그러나 LRR 문제를 해결하기 위해서는 알고리즘의 매 반복마다 데이터 수 크기의 정방행렬에 대해 특이값 분해를 수행하여야 하므로 계산 비효율적이다. 이를 해결하기 위해 속도를 향상시킨 발전된 LRR 방법을 제안한다. 이는 최근 발표된 Fast LRR(FaLRR)을 기반으로 하며, FaLRR이 속도는 빠르지만 실제로 분류 문제에서 성능이 낮은 것을 해결하기 위해 기반 최적화 목표에 추가 제약 조건을 도입하고 이를 최적화하는 방법을 제안한다. 실험을 통하여 제안 방법은 LRR보다 더 좋은 해를 빠르게 찾아냄을 확인할 수 있다. 또한, 동일한 해를 도출하는 방법을 찾아내기는 어렵지만 최소화하는 목표가 추가될 경우 더 좋은 결과를 나타내는 Fast MLRR(FaMLRR)을 제안한다.

• 한국초등수학교육학회지
• /
• 제14권1호
• /
• pp.123-134
• /
• 2010

본 논문에서는 평형저울을 이용하여 정확한 무게를 측정하기 위한 분동설계 과정에서 적용되는 수학적 내용 및 그 표현들에 대해 탐구하였다. 이 일련의 과정에서 일어날 수 있는 수학 장면과 아이디어 탐구, 2진법, 3진법의 2가지 다른 표현에 대한 이해 등을 포함한 구체적인 수학적 사고의 형성과정을 설명하고 분석한다. 이러한 과정을 현장에 적용하여 학습자의 수학적 사고의 발달과 수학적 성향을 개선시키는데 조금의 보탬이 되고자 하는데 그 목적이 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2590-2606
• /
• 2017

Generally, research of classical image classification algorithms assume that training data and testing data are derived from the same domain with the same distribution. Unfortunately, in practical applications, this assumption is rarely met. Aiming at the problem, a domain adaption image classification approach based on multi-sparse representation is proposed in this paper. The existences of intermediate domains are hypothesized between the source and target domains. And each intermediate subspace is modeled through online dictionary learning with target data updating. On the one hand, the reconstruction error of the target data is guaranteed, on the other, the transition from the source domain to the target domain is as smooth as possible. An augmented feature representation produced by invariant sparse codes across the source, intermediate and target domain dictionaries is employed for across domain recognition. Experimental results verify the effectiveness of the proposed algorithm.

• Educational Technology International
• /
• 제10권1호
• /
• pp.25-40
• /
• 2009

The purpose of this study was to explore procedures and modalities on collaborative visualization processing of text information for developing e-Learning contents. In order to investigate, two research questions were explored: 1) what are procedures on collaborative visualization processing of text information, 2) what kinds of patterns and modalities can be found in each procedure of collaborative visualization of text information. This research method was employed a qualitative research approaches by means of grounded theory. As a result of this research, collaborative visualization processing of text information were emerged six steps: identifying text, analyzing text, exploring visual clues, creating visuals, discussing visuals, elaborating visuals, and creating visuals. Collaborative visualization processing of text information came out the characteristic of systemic and systematic system like spiral sequencing. Also, another result of this study, modalities in collaborative visualization processing of text information was divided two dimensions: individual processing by internal representation, social processing by external representation. This case study suggested that collaborative visualization strategy has full possibility of providing ideal methods for sharing cognitive system or thinking system as using human visual intelligence.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제45권2호
• /
• pp.177-189
• /
• 2006

This study focuses on the analysis of prospective elementary teachers' representation of trapezoid area and teacher educator's reflecting in the context of a mathematics course. In this study, I use my own teaching and classroom of prospective elementary teachers as the site for investigation. 1 examine the ways in which my own pedagogical content knowledge as a teacher educator influence and influenced by my work with students. Data for the study is provided by audiotape of class proceeding. Episode describes the ways in which the mathematics was presented with respect to the development and use of representation, and centers around trapezoid area. The episode deals with my gaining a deeper understanding of different types of representations-symbolic, visual, and language. In conclusion, I present two major finding of this study. First, Each representation influences mutually. Prospective elementary teachers reasoned visual representation from symbolic and language. And converse is true. Second, Teacher educator should be prepared proper mathematical language through teaching and learning with his students.

• 대한수학교육학회지:학교수학
• /
• 제5권3호
• /
• pp.361-384
• /
• 2003

본 연구는 연립일차방정식에 관한 문장제에서 IDEAL 문제 해결 모형을 바탕으로 "구조-표현"을 강조한 교수-학습을 실시하였을 때 학생들의 문제해결 과정을 탐구하였다. 연구 결과, 구조-표현을 강조한 학급의 학생들이 이를 강조하지 않은 학급의 학생들보다 문제해결 능력이 향상되었으며, 동치문제, 동형문제, 유사문제를 더 정확하게 구별하였다. 또한, 구조-표현을 강조한 학급의 학생들이 그렇지 않은 학급의 학생들보다 문맥에 대한 이해 및 불완전한 정보 추출에서의 오류, 미지수간의 내적 관계에 대한 수학적 기호표현으로의 불완전한 전이 오류, 적절하지 않은 방정식 생성 오류의 발생 빈도가 적었다. 그리고, IDEAL 문제 해결 모형의 문제의 확인 단계(I)와 문제의 정의 단계(D)에서 학생들이 문제 해결 계획을 수립하기 위해 문제를 읽고 이해하여 문제를 해결하는 과정을 중점적으로 분석한 결과, 직접 변환 모델과 구조 도식 모델이 나타났다.