Time filter

Source Type

News Article | November 30, 2016
Site: www.newsmaker.com.au

Daejeon, KOREA - Exobrain, a language intelligence software for communicating between human and machine developed by the Electronics and Telecommunications Research Institute (ETRI), defeated four human champions in a quiz show on EBS Korea. South Korea's Educational Broadcasting System is a children's educational television and radio network. On November 18 Exobrain went "head-to-head" with human competitors on the television quiz show, "Janghak Quiz", which was recorded at the ETRI auditorium. Exobrain outpaced all competitors by scoring 510 out of 600 points, providing correct answers for 25 questions out of 30 (10 multiple-choice and 20 short-answer questions). The Exobrain defeated four human quiz prodigies: Mr. Yun Ju-il (finishing in 2nd place), a freshman of Seoul National University who attained a perfect score in last year's national college entrance exam; Mr. Kim Hyeon-ho and Miss Lee Jeong-min, the champions of the "Janghak Quiz" in the first and second half of 2016, respectively; and Mr. Oh Hyeon-min, who is studying mathematical sciences at KAIST and demonstrated his outstanding intelligence in a televised brain game.  Here's how Exobrain works: once a question is given, the system first derives keywords. For instance, in response to the question: "What is the stone tablet found in Egypt and described in Empire of the Ants, a novel written by Bernard Werber, which enabled communication between humans and ants?", the AI system searches such keywords as Werber, ants, communication, stone tablet and Egypt from its database before filtering tens to hundreds of possible answers. Next, it measures each potential answer against the question, assessing the reliability of each answer and finally submitting the most reliable answer. It only takes six to seven seconds to work out an answer.  In the quiz contest, Exobrain dominated the human competitors, but the system did not get all the answers right. The research team explained that Exobrain made a few wrong answers because some questions were related to fields the system had not learned about yet and the system did not have sufficient data to infer correct answers. The team added that further research and development would be required to conduct a semantic analysis of languages. According to ETRI, the core artificial intelligence (AI) technologies of Exobrain are: Korean language analysis technology, to analyze the grammar rules applied to sentences as its human counterparts can do; knowledge acquisition and exploration technology, to learn and store linguistic knowledge and unit of knowledge (a subject-predicate-object structure) from vast amount of books, documents, Wikipedia articles, dictionaries, and so on; and natural language QA technology, to understand questions comprising multiple sentences and infer answers. The quiz contest was intended to verify the level of first-stage technology developed over the first four years of the 10-year research period. The second and third stages of research are scheduled to be completed by 2022. For phase two, ETRI plans to focus on developing applied technologies and achieving globally competitive performance of QA solutions for expert knowledge including counseling, legal and patent areas. The last phase of the project will focus on developing QA solutions for expert knowledge in both Korean and English so that the AI system can engage in QA activities regarding expert knowledge described in English. In addition, ETRI researchers are committed to developing QA solutions for AI robots and wearable devices that can be utilized with a range of smart devices. Currently, Exobrain shows a level of performance similar to that of Watson, the AI system developed by IBM. In 2011, Watson appeared on the CBS quiz show "Jeopardy!" and defeated human quiz champions. Through further development, this AI system is now supporting the decision-making processes of medical, financial, and legal professionals.  ETRI aims to commercialize Exobrain within the next three years. Exobrain will be used to conduct prior analysis of areas requiring revision of law in partnership with the National Assembly Library, and the AI system is also expected to be used for filtering overlapping technologies in the process of screening patent applications.  "The correct answer rate of Exobrain is 83% on average, which is higher than Watson's performance (70%) in 2011," says Dr. Dong Won Han, Vice President of ETRI, SW and Contents Research Laboratory. "Considering that Exobrain was originally developed for the Korean language, it will have further potential uses when it is upgraded."  About ETRI Established in 1976, ETRI is a non-profit Korean government-funded research organization that has been at the forefront of technological excellence for about 40 years. In the 1980s, ETRI developed TDX (Time Division Exchange) and 4M DRAM. In the 1990s, ETRI commercialized CDMA (Code Division Multiple Access) for the first time in the world. In the 2000s, ETRI developed Terrestrial DMB, WiBro, and 4G LTE Advanced, which became the foundation of mobile communications. Recently, as a global ICT leader, ETRI has been advancing communication and convergence by developing SAN (Ship Area Network) technology, Genie Talk (world class portable automatic interpretation; Korean-English/Japanese/Chinese), and automated valet parking technology. As of 2016, ETRI has about 2,000 employees where about 1,800 of them are researchers. For more informatoin, please visit https://www.etri.re.kr/eng/main/main.etri For more information, please contact Dr. Hyun-ki Kim Director, Knowledge Mining Research Section, ETRI e-mail: [email protected] phone: +82 42 860 5965 Press release distributed by ResearchSEA on behalf of ETRI.


News Article | November 30, 2016
Site: www.acnnewswire.com

- Scholarship quiz show, called "Janghak Quiz", on the major educational television network in Korea - AI solutions to be developed for legal, patent and counseling areas Exobrain, a language intelligence software for communicating between human and machine developed by the Electronics and Telecommunications Research Institute (ETRI), defeated four human champions in a quiz show on EBS Korea. South Korea's Educational Broadcasting System is a children's educational television and radio network. On November 18 Exobrain went "head-to-head" with human competitors on the television quiz show, "Janghak Quiz", which was recorded at the ETRI auditorium. Exobrain outpaced all competitors by scoring 510 out of 600 points, providing correct answers for 25 questions out of 30 (10 multiple-choice and 20 short-answer questions). The Exobrain defeated four human quiz prodigies: Mr. Yun Ju-il (finishing in 2nd place), a freshman of Seoul National University who attained a perfect score in last year's national college entrance exam; Mr. Kim Hyeon-ho and Miss Lee Jeong-min, the champions of the "Janghak Quiz" in the first and second half of 2016, respectively; and Mr. Oh Hyeon-min, who is studying mathematical sciences at KAIST and demonstrated his outstanding intelligence in a televised brain game. Here's how Exobrain works: once a question is given, the system first derives keywords. For instance, in response to the question: "What is the stone tablet found in Egypt and described in Empire of the Ants, a novel written by Bernard Werber, which enabled communication between humans and ants?", the AI system searches such keywords as Werber, ants, communication, stone tablet and Egypt from its database before filtering tens to hundreds of possible answers. Next, it measures each potential answer against the question, assessing the reliability of each answer and finally submitting the most reliable answer. It only takes six to seven seconds to work out an answer. In the quiz contest, Exobrain dominated the human competitors, but the system did not get all the answers right. The research team explained that Exobrain made a few wrong answers because some questions were related to fields the system had not learned about yet and the system did not have sufficient data to infer correct answers. The team added that further research and development would be required to conduct a semantic analysis of languages. According to ETRI, the core artificial intelligence (AI) technologies of Exobrain are: Korean language analysis technology, to analyze the grammar rules applied to sentences as its human counterparts can do; knowledge acquisition and exploration technology, to learn and store linguistic knowledge and unit of knowledge (a subject-predicate-object structure) from vast amount of books, documents, Wikipedia articles, dictionaries, and so on; and natural language QA technology, to understand questions comprising multiple sentences and infer answers. The quiz contest was intended to verify the level of first-stage technology developed over the first four years of the 10-year research period. The second and third stages of research are scheduled to be completed by 2022. For phase two, ETRI plans to focus on developing applied technologies and achieving globally competitive performance of QA solutions for expert knowledge including counseling, legal and patent areas. The last phase of the project will focus on developing QA solutions for expert knowledge in both Korean and English so that the AI system can engage in QA activities regarding expert knowledge described in English. In addition, ETRI researchers are committed to developing QA solutions for AI robots and wearable devices that can be utilized with a range of smart devices. Currently, Exobrain shows a level of performance similar to that of Watson, the AI system developed by IBM. In 2011, Watson appeared on the CBS quiz show "Jeopardy!" and defeated human quiz champions. Through further development, this AI system is now supporting the decision-making processes of medical, financial, and legal professionals. ETRI aims to commercialize Exobrain within the next three years. Exobrain will be used to conduct prior analysis of areas requiring revision of law in partnership with the National Assembly Library, and the AI system is also expected to be used for filtering overlapping technologies in the process of screening patent applications. "The correct answer rate of Exobrain is 83% on average, which is higher than Watson's performance (70%) in 2011," says Dr. Dong Won Han, Vice President of ETRI, SW and Contents Research Laboratory. "Considering that Exobrain was originally developed for the Korean language, it will have further potential uses when it is upgraded." About ETRI Established in 1976, ETRI is a non-profit Korean government-funded research organization that has been at the forefront of technological excellence for about 40 years. In the 1980s, ETRI developed TDX (Time Division Exchange) and 4M DRAM. In the 1990s, ETRI commercialized CDMA (Code Division Multiple Access) for the first time in the world. In the 2000s, ETRI developed Terrestrial DMB, WiBro, and 4G LTE Advanced, which became the foundation of mobile communications. Recently, as a global ICT leader, ETRI has been advancing communication and convergence by developing SAN (Ship Area Network) technology, Genie Talk (world class portable automatic interpretation; Korean-English/Japanese/Chinese), and automated valet parking technology. As of 2016, ETRI has about 2,000 employees where about 1,800 of them are researchers. For more informatoin, please visit https://www.etri.re.kr/eng/main/main.etri For more information, please contact Dr. Hyun-ki Kim Director, Knowledge Mining Research Section, ETRI e-mail: phone: +82 42 860 5965 Press release distributed by ResearchSEA on behalf of ETRI. Topic: Research and development Sectors: Electronics, IT Individual, Science & Research http://www.acnnewswire.com From the Asia Corporate News Network


Lim J.-H.,SW and Contents Research Laboratory | Lee K.-C.,Chungnam National University
ETRI Journal | Year: 2015

Because protein is a primary element responsible for biological or biochemical roles in living bodies, protein function is the core and basis information for biomedical studies. However, recent advances in bio technologies have created an explosive increase in the amount of published literature; therefore, biomedical researchers have a hard time finding needed protein function information. In this paper, a classification system for biomedical literature providing protein function evidence is proposed. Note that, despite our best efforts, we have been unable to find previous studies on the proposed issue. To classify papers based on protein function evidence, we should consider whether the main claim of a paper is to assert a protein function. We, therefore, propose two novel features-protein and assertion. Our experimental results show a classification performance with 71.89% precision, 90.0% recall, and a 79.94% F-measure. In addition, to verify the usefulness of the proposed classification system, two case study applications are investigated-information retrieval for protein function and automatic summarization for protein function text. It is shown that the proposed classification system can be successfully applied to these applications. © 2015 ETRI.


Park J.,SW and Contents Research Laboratory | Lee S.-G.,Seoul National University
ETRI Journal | Year: 2016

Considerable attention has been given to processing graph data in recent years. An efficient method for computing the node proximity is one of the most challenging problems for many applications such as recommendation systems and social networks. Regarding large-scale, mutable datasets and user queries, top-κ query processing has gained significant interest. This paper presents a novel method to find top-κ answers in a node proximity search based on the well-κnown measure, Personalized PageRank (PPR). First, we introduce a distribution state transition graph (DSTG) to depict iterative steps for solving the PPR equation. Second, we propose a weight distribution model of a DSTG to capture the states of intermediate PPR scores and their distribution. Using a DSTG, we can selectively follow and compare multiple random paths with different lengths to find the most promising nodes. Moreover, we prove that the results of our method are equivalent to the PPR results. Comparative performance studies using two real datasets clearly show that our method is practical and accurate. © 2016 ETRI.


Yang U.,SW and Contents Research Laboratory | Kim N.-G.,Dong - Eui University | Kim K.-H.,SW and Contents Research Laboratory
ETRI Journal | Year: 2016

In the field of augmented reality technologies, commercial optical see-through-type wearable displays have difficulty providing immersive visual experiences, because users perceive different depths between virtual views on display surfaces and see-through views to the real world. Many cases of augmented reality applications have adopted eyeglasses-type displays (EGDs) for visualizing simple 2D information, or video see-through-type displays for minimizing virtual- and real-scene mismatch errors. In this paper, we introduce an innovative optical see-throughtype wearable display hardware, called an EGD. In contrast to common head-mounted displays, which are intended for a wide field of view, our EGD provides more comfortable visual feedback at close range. Users of an EGD device can accurately manipulate close-range virtual objects and expand their view to distant real environments. To verify the feasibility of the EGD technology, subjectbased experiments and analysis are performed. The analysis results and EGD-related application examples show that EGD is useful for visually expanding immersive 3D augmented environments consisting of multiple displays. © 2016 ETRI.


Choi J.-W.,SW and Contents Research Laboratory | Moon D.,SW and Contents Research Laboratory | Yoo J.-H.,SW and Contents Research Laboratory
ETRI Journal | Year: 2015

We propose a novel multiple-object tracking algorithm for real-time intelligent video surveillance. We adopt particle filtering as our tracking framework. Background modeling and subtraction are used to generate a region of interest. A two-step pedestrian detection is employed to reduce the computation time of the algorithm, and an iterative particle repropagation method is proposed to enhance its tracking accuracy. A matching score for greedy data association is proposed to assign the detection results of the two-step pedestrian detector to trackers. Various experimental results demonstrate that the proposed algorithm tracks multiple objects accurately and precisely in real time. © 2015 ETRI.


Park E.-J.,SW and Contents Research Laboratory | Kwon O.-W.,SW and Contents Research Laboratory | Kim K.,SW and Contents Research Laboratory | Kim Y.-K.,SW and Contents Research Laboratory
ETRI Journal | Year: 2015

In this paper, we propose a classification-based approach for hybridizing statistical machine translation and rule-based machine translation. Both the training dataset used in the learning of our proposed classifier and our feature extraction method affect the hybridization quality. To create one such training dataset, a previous approach used auto-evaluation metrics to determine from a set of component machine translation (MT) systems which gave the more accurate translation (by a comparative method). Once this had been determined, the most accurate translation was then labelled in such a way so as to indicate the MT system from which it came. In this previous approach, when the metric evaluation scores were low, there existed a high level of uncertainty as to which of the component MT systems was actually producing the better translation. To relax such uncertainty or error in classification, we propose an alternative approach to such labeling; that is, a cut-off method. In our experiments, using the aforementioned cut-off method in our proposed classifier, we managed to achieve a translation accuracy of 81.5% - a 5.0% improvement over existing methods. © 2015 ETRI.


Park H.S.,SW and Contents Research Laboratory | Kim K.-H.,IT Convergence Technology Research Laboratory
ETRI Journal | Year: 2015

This paper proposes an adaptive multimodal in-vehicle information system for safe driving. The proposed system filters input information based on both the priority assigned to the information and the given driving situation, to effectively manage input information and intelligently provide information to the driver. It then interacts with the driver using an adaptive multimodal interface by considering both the driving workload and the driver's cognitive reaction to the information it provides. It is shown experimentally that the proposed system can promote driver safety and enhance a driver's understanding of the information it provides by filtering the input information. In addition, the system can reduce a driver's workload by selecting an appropriate modality and corresponding level with which to communicate. An analysis of subjective questionnaires regarding the proposed system reveals that more than 85% of the respondents are satisfied with it. The proposed system is expected to provide prioritized information through an easily understood modality. © 2015 ETRI.


Yoon Y.,SW and Contents Research Laboratory | Ban K.-D.,SW and Contents Research Laboratory | Yoon H.,SW and Contents Research Laboratory | Kim J.,SW and Contents Research Laboratory
ETRI Journal | Year: 2016

Automatic container code recognition from a captured image is used for tracking and monitoring containers, but often fails when the code is not captured clearly. In this paper, we increase the accuracy of container code recognition using multiple views. A character-level integration method combines recognized codes from different single views to generate a new code. A decisionlevel integration selects the most probable results from the codes from single views and the new integrated code. The experiment confirmed that the proposed integration works successfully. The recognition from single views achieved an accuracy of around 70% for the test images collected on a working pier, whereas the proposed integration method showed an accuracy of 96%. © 2016 ETRI.


Lee S.,SW and Contents Research Laboratory | Choi D.,Korean University of Science and Technology | Choi Y.-J.,SW and Contents Research Laboratory
ETRI Journal | Year: 2015

Conventional cryptographic algorithms are not sufficient to protect secret keys and data in white-box environments, where an attacker has full visibility and control over an executing software code. For this reason, cryptographic algorithms have been redesigned to be resistant to white-box attacks. The first white-box AES (WB-AES) implementation was thought to provide reliable security in that all brute force attacks are infeasible even in white-box environments; however, this proved not to be the case. In particular, Billet and others presented a cryptanalysis of WB-AES with 230 time complexity, and Michiels and others generalized it for all substitution-linear transformation ciphers. Recently, a collision-based cryptanalysis was also reported. In this paper, we revisit Chow and others's first WB-AES implementation and present a conditional re-encoding method for cryptanalysis protection. The experimental results show that there is approximately a 57% increase in the memory requirement and a 20% increase in execution speed. © 2015 ETRI.

Loading SW and Contents Research Laboratory collaborators
Loading SW and Contents Research Laboratory collaborators