• Journal of Korean Library and Information Science Society
• /
• v.46 no.1
• /
• pp.321-344
• /
• 2015

This paper presents a fusion approach to sentiment detection that combines multiple sources of evidence to retrieve blogs that contain opinions on a specific topic. Our approach to finding opinionated blogs on topic consists of first applying traditional information retrieval methods to retrieve blogs on a given topic and then boosting the ranks of opinionated blogs based on the opinion scores computed by multiple sentiment detection methods. Our sentiment detection strategy, whose central idea is to rely on a variety of complementary evidences rather than trying to optimize the utilization of a single source of evidence, includes High Frequency module, which identifies opinions based on the frequency of opinion terms (i.e., terms that occur frequently in opinionated documents), Low Frequency module, which makes use of uncommon/rare terms (e.g., "sooo good") that express strong sentiments, IU Module, which leverages n-grams with IU (I and you) anchor terms (e.g., I believe, You will love), Wilson's lexicon module, which uses a collection-independent opinion lexicon constructed from Wilson's subjectivity terms, and Opinion Acronym module, which utilizes a small set of opinion acronyms (e.g., imho). The results of our study show that combining multiple sources of opinion evidence is an effective method for improving opinion detection performance.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2001.06a
• /
• pp.97-109
• /
• 2001

이 논문은 영어와 한국어에서 나타나는 완수동사(Accomplishment Verb)와 지속부사구(durative adverbial)의 상호작용에 대해서 논한다. Smith(1991)에 의하면 완수동사가 지속부사구와 결합하면, 동사와 부사구의 의미적 자질의 충돌을 피하기 위해서 완수동사의 상변환(Apsect Shift)이 일어난다. 본 논문은 이 상변환이 영어와 한국어에서 어떻게 실현되는가를 보이고, 이를 형식의미론에서 어떻게 기술할 수 있는가를 논한다. 완수동사가 지속부사구와 결합할 때, 영어와 한국어 모두에서 닫힌 완료 관점(closed perfective viewpoint)에서 열린 관점(open viewpoint)으로 관점 변환(viewpoint shift)이 일어난다. 그러나, 한국어의 상변환과 영어의 상변환이 완전히 일치하는 것은 아니다. 한국어의 관점변환은 완료관점도 아니고 미완료 관점도 아닌, 중립관점(neutral viewpoint)으로의 변환인 반면, 영어의 관점변환은 단순히 미완료 관점으로의 변환임이 논의된다. 이 주장은 한국어의 관점변환 구문은 이질적인 다수 사건의 연속 해석(heterogeneous sequential reading of multiple events)을 허용하는 반면, 영어의 관점변환구문은 오직 동질적인 단일 사건의 동시 해석 (homogeneous simultaneous reading of a single event)만을 허용한다는 사실에 의해서 지지 된다. 본 논문은 완수동사가 지속부사구와 결합할 때 일어나는 상변환에 대한 형식의 미론 분석을 Heim ＆ Kratzer (1998)의 틀에서 제시한다. 닫힌 관점에서 열린 관점으로의 상변환은 비가시적 시제 서법 운용자(covert temporal-modal operator)인 IMP를 지속부사구의 논항으로 설정하여 설명한다. IMP는 Dowty (1979)에서 미완료상의 모순(imperfective paradox)을 해결하기 위해서 설정한 PROG를 Heim ＆ Kratzer (1998)의 틀에 맞게 수정한 것이다. IMP는 평가 세계 (evaluation world)를 현실 세계(actual world)에서 가상 관성 세계(possible inertia would)로 변화시켜서, 완수동사의 종결점(ending point)을 현실세계에서 가상의 미래 세계로 움직이는 역할을 한다. 결과적으로, IMP는 완수동사의 닫힌 완료 관점을 현실세계에서는 열린 미완료 관점으로 변환시키되, 가상 관성 세계에서는 그대로 닫힌 관점으로 유지 시키는 효과를 가진다. 한국어와 영어의 관점 변환 구문의 차이는 각 언어의 지속부사구의 어휘 목록의 전제(presupposition)의 차이로 설명된다. 본 논문은 영어의 지속부사구는 논항의 하위간격

• Korean Journal of Cognitive Science
• /
• v.17 no.1
• /
• pp.15-27
• /
• 2006

The effects of the number of Hangul syllable, the nunber/location of batchim in a Hangul word, and compound/noncompound Hangul word on memory span were examined. The results were that (1) the more syllables a word had, the lower us memory span was, (2) the more batchims a two-syllable word had, the lower its memory span was (Korean batchim effect on memory span), (3) noncompound word had higher memory span than compound word. The reading speed of above mentioned words was measured and the results were that (1) the more syllables a word had, the slower its reading speed was, (2) but the reading speed of a two-syllable word was forest when it had a batchim on second syllable than when it had no batchim or had a batchim on first syllable or batchims on both syllables (Korean ending batchim effect on reading speed), (3) noncompound word was read faster thu compound word. Korean ending batchim effect on reading speed was not compatible with the explanation by articulatory loop bur compatible with the explanation by visual cache where the orthographic information was represented. The results suggest that memory span was influenced nor only by phonological information but also by orthographic information.

• Korean Journal of Cognitive Science
• /
• v.19 no.4
• /
• pp.499-517
• /
• 2008

In this paper, we propose an effective emotion feature extraction method for Korean and evaluate their availability in sentiment classification. Korean emotion features are expanded from several representative emotion words and they play an important role in building in an effective sentiment classification system. Firstly, synonym information of English word thesaurus is used to extract effective emotion features and then the extracted English emotion features are translated into Korean. To evaluate the extracted Korean emotion features, we represent each document using the extracted features and classify it using SVM(Support Vector Machine). In experimental results, the sentiment classification system using the extracted Korean emotion features obtained more improved performance(14.1%) than the system using content-words based features which have generally used in common text classification systems.

• Journal of The Korean Association of Information Education
• /
• v.6 no.3
• /
• pp.266-278
• /
• 2002

The purpose of this study is to help cultivating Children's sensibility through the development of typing program which shows vocabulary of sensibility. The characteristic of this typing education program is designed to finish the game when the children get the certain point by typing the words on the screen(from the top to the bottom) within the limit of time. For examples, adjectives in the Korean dictionary, the words of modern & traditional children's songs, imitative words and echoic words through this game, the children are fully aware of the meaningful words without realizing it. Through this game, the children are fully a ware of the meaningful words without recognizing it. After application of this typing education program children were fully aware of meaningful words more than meaningless words. After examining the survey of children we could discover that this typing program help cultivating children's sensibility.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.5
• /
• pp.970-976
• /
• 2001

In this paper, OUIG IDL CFE, provided by Sunsoft, is used to take a IDL definitions as inputs and parse those. OmniORB3 is introduced to support functionality of the ORB. Suns CFE produce AST after parsing inputs. Actually, the node of AST Is instances of classes which are derived from CFE classes. As the compiler back end visit the node of the AST using iterator class, UTL_ScopeActiveIterator, it dumps codes of output. During processing, two files are generated. Routines of generating code are invoked by BE_produce.cc and codes are produced while visiting root of AST, idl_global->root(). The dump* functions which dump codes is called according to the type of node. In this paper, Mapping C++ of IDL definition is experimented and results In the same as that of omniidl which is provided by omniORB3. The code of results behavior correctly on omniORB3. In the future, we are interested in optimizing the performance of marshalling code via IDL compiler.

• The KIPS Transactions:PartD
• /
• v.9D no.6
• /
• pp.1091-1096
• /
• 2002

This paper presents the development of a protein interaction database. The developed system is characterized as follows. First, the proposed system not only maintains interaction data collected by an experiment, but also the genomic information of the protein data. Secondly, the system can extract details on interacting proteins through the developed wrappers. Thirdly, the system is based on wrapper-based system in order to extract the biologically meaningful data from various web sources and integrate them into a relational database. The system inherits a layered-modular architecture by introducing a wrapper-mediator approach in order to solve the syntactic and semantic heterogeneity among multiple data sources. Currently the system has wrapped the relevant data for about 40% of about 11,500 proteins on average from various accessible sources. A wrapper-mediator approach makes a protein interaction data comprehensive and useful with support of data interoperability and integration. The developing database will be useful for mining further knowledge and analysis of human life in proteomics studies.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.10
• /
• pp.457-464
• /
• 2014

Foreign language learners want to remember newly learned vocabularies for as long as possible. As demand for learning English as a second language grows, effective ways of memorizing English vocabularies also attract much interest so that various methods and apparatus are developed in order to support effective memorization. In this research, we introduce a new way of memorizing English vocabularies and evaluate the performance compared to an existing qualified method. Our study result shows that learners who memorize English words using our suggested method maintained a higher retention rate than those who studied using the existing method. From this research, we expect to gain new insights of effective way in learning English vocabularies.

• Journal of KIISE:Software and Applications
• /
• v.36 no.1
• /
• pp.82-91
• /
• 2009

Sign language spotting is the task of detecting and recognizing the signs in a signed utterance. The difficulty of sign language spotting is that the occurrences of signs vary in both motion and shape. Moreover, the signs appear within a continuous gesture stream, interspersed with transitional movements between signs in a vocabulary and non-sign patterns(which include out-of-vocabulary signs, epentheses, and other movements that do not correspond to signs). In this paper, a novel method for designing a threshold model in a conditional random field(CRF) model is proposed. The proposed model performs an adaptive threshold for distinguishing between signs in the vocabulary and non-sign patterns. A hand appearance-based sign verification method, a short-sign detector, and a subsign reasoning method are included to further improve sign language spotting accuracy. Experimental results show that the proposed method can detect signs from continuous data with an 88% spotting rate and can recognize signs from isolated data with a 94% recognition rate, versus 74% and 90% respectively for CRFs without a threshold model, short-sign detector, subsign reasoning, and hand appearance-based sign verification.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.674-679
• /
• 2017

In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.