• ETRI Journal
• /
• v.46 no.1
• /
• pp.82-95
• /
• 2024

As automated essay scoring (AES) has progressed from handcrafted techniques to deep learning, holistic scoring capabilities have merged. However, specific trait assessment remains a challenge because of the limited depth of earlier methods in modeling dual assessments for holistic and multi-trait tasks. To overcome this challenge, we explore providing comprehensive feedback while modeling the interconnections between holistic and trait representations. We introduce the DualBERT-Trans-CNN model, which combines transformer-based representations with a novel dual-scale bidirectional encoder representations from transformers (BERT) encoding approach at the document-level. By explicitly leveraging multi-trait representations in a multi-task learning (MTL) framework, our DualBERT-Trans-CNN emphasizes the interrelation between holistic and trait-based score predictions, aiming for improved accuracy. For validation, we conducted extensive tests on the ASAP++ and TOEFL11 datasets. Against models of the same MTL setting, ours showed a 2.0% increase in its holistic score. Additionally, compared with single-task learning (STL) models, ours demonstrated a 3.6% enhancement in average multi-trait performance on the ASAP++ dataset.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.25-29
• /
• 2019

딥러닝을 이용한 한국어 의존 파싱은 전이 기반 방식과 그래프 기반 방식으로 나뉘어 연구되어 왔다. 전이 기반 방식은 입력 버퍼와 스택으로부터 자질을 추출하여 모델을 통해 액션을 결정하고 액션에 따라 파스트리를 생성해 나가는 상향식(Botton-Up)의 지역적 모델이고 그래프 기반 방식은 문장 내의 모든 단어에 대해 지배소, 의존소가 될 수 있는 점수를 딥러닝 모델을 통해 점수화하여 트리를 생성하는 전역적 모델이다. 본 논문에서는 Dual Decomposition을 이용하여 하이브리드 방식으로 전이 기반 파서와 그래프 기반 파서를 결합하는 방법을 제안하고 BERT 언어 모델을 반영하여 세종 데이터 셋에서 UAS 94.47%, LAS 92.58% 그리고 SPMRL '14 데이터 셋에서 UAS 94.74%, UAS 94.20%의 성능을 보여 기존 그래프 기반 파서의 성능을 더욱 개선하였다.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.21 no.45
• /
• pp.93-100
• /
• 1998

The researches of Linear Programming are Khachiyan Method, which uses Ellipsoid Method, and Karmarkar, Affine, Path-Following and Interior Point Method which have Polynomial-Time complexity. In this study, Karmarkar Method is more quickly solved as 50 times then Simplex Method for optimal solution. but some special problem is not solved by Karmarkar Method. As a result, the algorithm by APL Language is proved time efficiency and optimal solution in the Primal-Dual interior point algorithm. Furthermore Karmarkar Method and Primal-Dual interior point Method is compared in some examples.

• Journal of the Korean association of regional geographers
• /
• v.23 no.2
• /
• pp.354-365
• /
• 2017

This study is to analyze the dual language and hybrid identity of the students of Daegu Chinese Middle.High School. Such a phenomenon is being produced and changed at the site or zone of meeting different or conflict factors such as Chinese and Korean. The Chinese Korean students had learned Korean from their mother and her relative at a young age, and their dual and complex language habit was produced due to the learning of Chinese from father and his relative. A large number of the students were educated at a Korean kindergarten, but they were formally learned Chinese and China's society and culture at a Korean Chinese school after primary school. The Chinese Korean students talk with parents, brother and sister, teacher, friend and neighbor at home, school and local by Chinese and/or Korean. They use a dual language of Chinese and Korean based on various situations, but they do not particularly distinguished both language in cognition. The students have a hybrid identity of simultaneously recognizing Chinese and Korean. But some of them think Chinese or Korean. It is necessary for the results of this study to be objectified from the following research on the students of Chinese Middle･High School in Seoul, Incheon and Busan.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.41-44
• /
• 2017

기계이해 시스템은 주어진 문서를 이해하고 질의에 해당하는 정답을 출력하는 방법으로 심층 신경망을 활용한 주의집중 방법이 발달하면서 활발히 연구되기 시작했다. 본 논문에서는 어휘 정보를 통해 문서와 질의를 이해하는 어휘 이해 모델과 품사 등장 정보, 의존 구문 정보를 통해 문법적 이해를 하는 구문 이해 모델을 함께 사용하여 기계이해 질의응답을 하는 Dual Bi-Directional Attention Flow모델을 제안한다. 한국어로 구성된 18,863개 데이터에서 제안 모델은 어휘 이해 모델만 사용하는 Bi-Directional Attention Flow모델보다 높은 성능(Exact Match: 0.3529, F1-score: 0.6718)을 보였다.

• Archives of design research
• /
• v.20 no.1 s.69
• /
• pp.55-64
• /
• 2007

Non-verbal communications are important because they support and replace verbal communication. Body language of various non-verbal communications is the communication using the body. In animation, expression of body language is very important because characters play an important role in communicating the scenario. Animation has a dual communication structure, different from general communication. One is the communication between the speaker character and the hearer character, the other is the image and the audience, which includes the communication between the speaker character and the hearer character. In this study, we divide the body language from the characters into the discourse-in act and discourse-out act according to this dual structure and classify it into adaptors, emblem, illustrator, regulator, affect display by a functional approach method. Especially, the illustrator is subdivided into pragmatic speech act. Finally, this study analyzes the features of body language in animation and represents animation character's body language for an effective expression of the communications in animation.

• Journal of Korean language education
• /
• v.23 no.1
• /
• pp.257-282
• /
• 2012

Sakhalin, Russia is a very specific area for Korean language education. The imposed separation and isolation in this region means the language in Sakhalin is mixed with South Korean, North Korean, Gyeongsang Province dialect, Japanese, and Russian. Scrutiny of the use of the actual language of Sakhalin Koreans is needed, and it is required in supporting Korean language education. In this study, I will cover: 1. Approach should differ depending on the situation of Korean, foreigners, Korean Language School(Hangeul Hakgyo) and Korean classes in local Schools. 2. Tailor-made textbooks for Sakhalin are required. 3. Korean textbooks to match local circumstances are needed. There should be a basic writing text written by a local Korean department professor and supervision or modification, supplements from Korean language education researchers in Korea. 4. Enlarged Korean training programs are needed. Furthermore, if Korean and Russian university students are to study in Korea, there should be programs offering a dual degree among other things. 5. Methodical, overall examination of overseas Korean regions like Sakhalin is necessary. Also in the case of far east Russia, connectivity between Vladivostok, Khabarovsk and Sakhalin needs to be strengthened.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.49-53
• /
• 2019

챗봇은 사람과 컴퓨터가 자연어로 대화를 주고받는 시스템을 말한다. 최근 챗봇에 대한 연구가 활발해지면서 단순히 기계적인 응답보다 사용자가 원하는 개인 특성이 반영된 챗봇에 대한 연구도 많아지고 있다. 기존 연구는 하나의 벡터를 사용하여 한 가지 형태의 페르소나 정보를 모델에 반영했다. 하지만, 페르소나는 한 가지 형태로 정의할 수 없어서 챗봇 모델에 페르소나 정보를 다양한 형태로 반영시키는 연구가 필요하다. 따라서, 본 논문은 최신 생성 기반 Multi-Turn 챗봇 시스템을 기반으로 챗봇이 다양한 형태로 페르소나를 반영하게 하는 방법을 제안한다.

• Journal of English Language & Literature
• /
• v.56 no.6
• /
• pp.1135-1161
• /
• 2010

The interpretations of degree expressions require the postulation of new entities to represent degrees. Diverse entities such as degrees, intervals, and vectors are adopted for degree expressions. Positive degree sentences and questions are properly construed with the introduction of these entities, but their negative counterparts need more consideration. Negative degree sentences show dual patterns of entailments depending on contexts, and negative degree questions are unacceptable, making weak islands. To explicate the distinct nature of negative degree sentences and questions, Fox & Hackl (2006) provide an analysis based on degrees while Abrusan & Spector (2010) suggest a proposal in interval readings of degree expressions. I have pointed out the theoretical problems of these analyses and proposed an alternative in the framework of the vector space semantics, following Winter (2005). Bi-directional scales in vector space fit well with the dual patterns of negative degree sentences, and the notion of a reference vector is useful to accommodate the contextual influence in negative degree sentences and to deal with the unacceptability of negative degree questions.

• English Language & Literature Teaching
• /
• v.10 no.1
• /
• pp.53-76
• /
• 2004

This paper introduces a class model based on a course, Internet English, offered by an English department at a university. The course has dual purposes of developing students I English skills and Internet using skills at the same time. In support of using the Internet for language learning, the advantages of project-based language learning and constructivist learning in relation to CALL are explored. The activities in this course, which are basically project-based under the paradigm of constructivist learning perspective, are explained in detail to show the relationship between second language learning theory and teaching application. The way how the four language skills - speaking, listening, reading, and writing - are integrated in this class is described as well. Finally, judgmental evaluation of the course by the students is noted. The results show that a project-based CALL class could be a promising class model to realize an integrative, constructivist, and authentic learning.