Chikara Hashimoto, Daisuke Kawahara, Takayuki Yoshida, Hiroki Goto, S. Yokoyama
This paper deals with parser adaptation to patent domain. Our adaptation method utilizes case frames that are compiled automatically from patent documents. We show that our method works well for adapting a parser to patent domain and that, in order to adapt a parser to a patent sub-domain like digital data processing, we can use different sub-domains like microbe/ferment and machinery to some extent.
{"title":"Parser Adaptation to Patent Domain Exploiting Case Frames","authors":"Chikara Hashimoto, Daisuke Kawahara, Takayuki Yoshida, Hiroki Goto, S. Yokoyama","doi":"10.1109/ISUC.2008.24","DOIUrl":"https://doi.org/10.1109/ISUC.2008.24","url":null,"abstract":"This paper deals with parser adaptation to patent domain. Our adaptation method utilizes case frames that are compiled automatically from patent documents. We show that our method works well for adapting a parser to patent domain and that, in order to adapt a parser to a patent sub-domain like digital data processing, we can use different sub-domains like microbe/ferment and machinery to some extent.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131793079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Query-recommendation systems based on inputted queries have become widespread. These services are effective if users cannot input relevant queries. However, the conventional systems do not take into consideration the relevance between recommended queries. This paper proposes a method of obtaining related queries and clustering them by using the history of query frequencies in query logs. We define similarity in queries based on the history of query frequency and use it for clustering queries. We selected various queries and extracted related queries and then clustered them. We found that our method was useful for clustering queries that were used in around the same term.
{"title":"Extracting and Clustering Related Keywords based on History of Query Frequency","authors":"Toru Onoda, T. Yumoto, K. Sumiya","doi":"10.1109/ISUC.2008.22","DOIUrl":"https://doi.org/10.1109/ISUC.2008.22","url":null,"abstract":"Query-recommendation systems based on inputted queries have become widespread. These services are effective if users cannot input relevant queries. However, the conventional systems do not take into consideration the relevance between recommended queries. This paper proposes a method of obtaining related queries and clustering them by using the history of query frequencies in query logs. We define similarity in queries based on the history of query frequency and use it for clustering queries. We selected various queries and extracted related queries and then clustered them. We found that our method was useful for clustering queries that were used in around the same term.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131381092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Kurohashi, Susumu Akamine, Daisuke Kawahara, Yoshikiyo Kato, Tetsuji Nakagawa, Kentaro Inui, Y. Kidawara
As computers and computer networks become more sophisticated, a vast amount of information and knowledge has been accumulated and circulated on the Web. They provide people with options regarding their daily lives and are starting to have a strong influence on governmental policies and business management. However, a crucial problem is that information on the Web is not necessarily credible. It is actually very difficult for human beings to judge information credibility and even more difficult for computers. However, computers can be used to develop a system that collects, organizes and relativises information and helps human beings view information from several viewpoints and judge information credibility. This paper introduces the information credibility criteria project at the National Institute of Information and Communications Technology, which aims to develop such a system, called WISDOM.
{"title":"Information Credibility Analysis of Web Contents","authors":"S. Kurohashi, Susumu Akamine, Daisuke Kawahara, Yoshikiyo Kato, Tetsuji Nakagawa, Kentaro Inui, Y. Kidawara","doi":"10.1109/ISUC.2008.79","DOIUrl":"https://doi.org/10.1109/ISUC.2008.79","url":null,"abstract":"As computers and computer networks become more sophisticated, a vast amount of information and knowledge has been accumulated and circulated on the Web. They provide people with options regarding their daily lives and are starting to have a strong influence on governmental policies and business management. However, a crucial problem is that information on the Web is not necessarily credible. It is actually very difficult for human beings to judge information credibility and even more difficult for computers. However, computers can be used to develop a system that collects, organizes and relativises information and helps human beings view information from several viewpoints and judge information credibility. This paper introduces the information credibility criteria project at the National Institute of Information and Communications Technology, which aims to develop such a system, called WISDOM.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123229875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this era of information explosion, information retrieval engines are indispensable to the Internet users. However, in current search services, there are some practical problems. That is, search engines do not analyze information from the user's viewpoint. Under this premise, our program "Very Large Information Integration and Application Platform" plans to construct a safe and intelligent platform for information retrieval. Through the collaboration of four government ministries' sponsored projects in Japan, such a platform would contribute toward the development of an information-rich society.
{"title":"Very Large Information Integration and Application Platform - CSTP Coordination Program of Science and Technology Projects - (Invited Paper)","authors":"S. Nishio","doi":"10.1109/ISUC.2008.77","DOIUrl":"https://doi.org/10.1109/ISUC.2008.77","url":null,"abstract":"In this era of information explosion, information retrieval engines are indispensable to the Internet users. However, in current search services, there are some practical problems. That is, search engines do not analyze information from the user's viewpoint. Under this premise, our program \"Very Large Information Integration and Application Platform\" plans to construct a safe and intelligent platform for information retrieval. Through the collaboration of four government ministries' sponsored projects in Japan, such a platform would contribute toward the development of an information-rich society.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125208389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes an Internet environment called BrailleMUSE to translate digital music scores into Braille scores. In experiments with expert translators, a translation error occurred only at extremely slight frequency. Moreover, the experts reported that working hours to produce Braille scores were shortened as the drafts the BrailleMUSE provided were only modified. Also, the BrailleMUSE has a mirror page to a music site showing about 4,000 digital scores. It was confirmed that the system provided Braille scores by working together with the music site. It is suggested that the system is suitable for practical use.
{"title":"An Internet Environment for Braille Translation of Digital Music Scores","authors":"T. Gotoh, R. Minamikawa-Tachino, N. Tamura","doi":"10.1109/ISUC.2008.25","DOIUrl":"https://doi.org/10.1109/ISUC.2008.25","url":null,"abstract":"This paper proposes an Internet environment called BrailleMUSE to translate digital music scores into Braille scores. In experiments with expert translators, a translation error occurred only at extremely slight frequency. Moreover, the experts reported that working hours to produce Braille scores were shortened as the drafts the BrailleMUSE provided were only modified. Also, the BrailleMUSE has a mirror page to a music site showing about 4,000 digital scores. It was confirmed that the system provided Braille scores by working together with the music site. It is suggested that the system is suitable for practical use.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126286442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gabriel Pablo Nava, K. Hirata, M. Miyoshi, Yasunori Harada
Traditional videoconferencing systems that work on the basis of face-to-face configurations allow the use of standard 2-channel stereo loudspeakers in order to achieve sound-image localization by the users. In contrast, immersive systems that do not constraint the users to a face-to-face viewpoint introduce new challenges in their acoustic design. This paper discusses the major problems that appear in a novel videoconferencing system in which the use of ordinary 2-channel loudspeakers is not suitable to achieve sound-image localization due to the inherent characteristics of the room space. In efforts to overcome these problems, a loudspeaker-embedded design is proposed and demonstrated with numerical simulations and experiments that show the steady-state sound field radiated by this new loudspeaker system.
{"title":"A Loudspeaker-Embedded Design for an Immersive Videoconferencing System with Large Screens","authors":"Gabriel Pablo Nava, K. Hirata, M. Miyoshi, Yasunori Harada","doi":"10.1109/ISUC.2008.50","DOIUrl":"https://doi.org/10.1109/ISUC.2008.50","url":null,"abstract":"Traditional videoconferencing systems that work on the basis of face-to-face configurations allow the use of standard 2-channel stereo loudspeakers in order to achieve sound-image localization by the users. In contrast, immersive systems that do not constraint the users to a face-to-face viewpoint introduce new challenges in their acoustic design. This paper discusses the major problems that appear in a novel videoconferencing system in which the use of ordinary 2-channel loudspeakers is not suitable to achieve sound-image localization due to the inherent characteristics of the room space. In efforts to overcome these problems, a loudspeaker-embedded design is proposed and demonstrated with numerical simulations and experiments that show the steady-state sound field radiated by this new loudspeaker system.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121739777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the growth of massive information on the Web, information recommendation and filtering techniques have been studied intensively.Traditional route search systems, which can be considered one of information recommendation systems, usually calculate the shortest path in terms of time or distance.Recently, route search systems for more general purposes have become an important research topic.In this paper we propose an efficient tourist route search system which not only recommends the path simply connecting several tourist spots, but also recommends the path with beautiful scenic sights.We focus on the visibility of scenic sights between one tourist spot and another, which is an important factor for choosing a driving route, but has not been considered in traditional tourist navigation systems.To automatically retrieve tourist spots, we propose a personalized tourist spot recommendation technique using the Web information.To find a route with attractive scenery, scores for paths based on the visibility of scenic sights are calculated and utilized.We tested the effectiveness of the proposed system by using a prototype of the system.
{"title":"A Tourist Route Search System Based on Web Information and the Visibility of Scenic Sights","authors":"Jianwei Zhang, Hiroshi Kawasaki, Yukiko Kawai","doi":"10.1109/ISUC.2008.19","DOIUrl":"https://doi.org/10.1109/ISUC.2008.19","url":null,"abstract":"With the growth of massive information on the Web, information recommendation and filtering techniques have been studied intensively.Traditional route search systems, which can be considered one of information recommendation systems, usually calculate the shortest path in terms of time or distance.Recently, route search systems for more general purposes have become an important research topic.In this paper we propose an efficient tourist route search system which not only recommends the path simply connecting several tourist spots, but also recommends the path with beautiful scenic sights.We focus on the visibility of scenic sights between one tourist spot and another, which is an important factor for choosing a driving route, but has not been considered in traditional tourist navigation systems.To automatically retrieve tourist spots, we propose a personalized tourist spot recommendation technique using the Web information.To find a route with attractive scenery, scores for paths based on the visibility of scenic sights are calculated and utilized.We tested the effectiveness of the proposed system by using a prototype of the system.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129987859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper we propose a novel approach for understanding human actions in daily life scene by decomposing the human motions into actions primitive using the definition of the motion verb in dictionary and representing the relationship of the action words using Bayesian network. Because there are so many variant of human motions and the difficulty in naming the human motion in daily life, we propose to use the word definition in dictionary in order to give the appropriate vocabulary for the actions and modeling the human actions. In this method, we can decompose the human actions into smaller primitive motions and give a name to each motion according to the definition from the dictionary. Another advantage of this method is that we can use only small amount of training data for the smallest primitive motion that can be related directly with the features from the image or sequence of images and by incorporating some predefined knowledge. We implement the proposed methods to recognize several human actions in daily life which can be divided into 3 categories : action without object or interaction with other human (e.g., walking, sitting, etc.), action with object (e.g., grasping, picking up, etc.), and action which interact with other human (e.g., shaking hands, etc.). We shows the proposed method can be used to recognize actions in daily life by inferring the Bayesian network based on the evidence(s) from input images sequence.
{"title":"Understanding Human Action in Daily Life Scene based on Action Decomposition using Dictionary Terms and Bayesian Network","authors":"J. Lokman, Jun-ichi Imai, M. Kaneko","doi":"10.1109/ISUC.2008.53","DOIUrl":"https://doi.org/10.1109/ISUC.2008.53","url":null,"abstract":"In this paper we propose a novel approach for understanding human actions in daily life scene by decomposing the human motions into actions primitive using the definition of the motion verb in dictionary and representing the relationship of the action words using Bayesian network. Because there are so many variant of human motions and the difficulty in naming the human motion in daily life, we propose to use the word definition in dictionary in order to give the appropriate vocabulary for the actions and modeling the human actions. In this method, we can decompose the human actions into smaller primitive motions and give a name to each motion according to the definition from the dictionary. Another advantage of this method is that we can use only small amount of training data for the smallest primitive motion that can be related directly with the features from the image or sequence of images and by incorporating some predefined knowledge. We implement the proposed methods to recognize several human actions in daily life which can be divided into 3 categories : action without object or interaction with other human (e.g., walking, sitting, etc.), action with object (e.g., grasping, picking up, etc.), and action which interact with other human (e.g., shaking hands, etc.). We shows the proposed method can be used to recognize actions in daily life by inferring the Bayesian network based on the evidence(s) from input images sequence.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132419664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper describes a new memory aid technique using wearable devices to augment human memory. The system utilizes videos and still images to effectively enforces memorization process for later recall. The goal of the system is to exploit infinite capacity of human memory by assisting memorization to expand a virtual memory space using video and images captured and annotated during interaction process to real-world information. We conducted a basic model experiment to demonstrate our idea. The result suggested that the optimized video replay composed based on the task segmentation aided memorization very intensely to successfully construct an effective memory space.
{"title":"Wearable Memorization Aid for Human Memory Augmentation","authors":"Y. Ikei, Kenji Ishigaki","doi":"10.1109/ISUC.2008.72","DOIUrl":"https://doi.org/10.1109/ISUC.2008.72","url":null,"abstract":"This paper describes a new memory aid technique using wearable devices to augment human memory. The system utilizes videos and still images to effectively enforces memorization process for later recall. The goal of the system is to exploit infinite capacity of human memory by assisting memorization to expand a virtual memory space using video and images captured and annotated during interaction process to real-world information. We conducted a basic model experiment to demonstrate our idea. The result suggested that the optimized video replay composed based on the task segmentation aided memorization very intensely to successfully construct an effective memory space.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133760643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Up to now, the method to reduce the ambiguity of phoneme recognition using 2nd-order Markov chain model of phonemes, has been proposed and has been evaluated by phonem lattice simulated and limited to substitution error. However, the method will be necessary to demonstrate the effectiveness for the phoneme candidate lattice obtained by actual speech recognition devices. This paper deals with recurrent neural networks(RNN) which are well- suited for natural language processing of speech recognition, specially for phoneme recognition. The ability of these networks has been investigated by phoneme recognition experiments using a number of Japanese words uttered by a native male speaker in a quiet environment. A method to detect the locations of devoicing vowels using the short- time average energy has been also proposed, and evaluated. Form results of the experiments, it is shown that recognition rates achieved with RNN are higher than those obtained with conventional non-recurrent neural networks, and that the method to detect the locations of devoicing vowels is useful.
{"title":"A New Method to Reduce the Ambiguity of Japanese Phoneme Candidates Recognized by Recurrent Neural Networks","authors":"Shin-ichiro Hashimukai, Chikahiro Araki, Mikio Mori, S. Taniguchi, Shozo Kato, Yasuhiro Ogoshi","doi":"10.1109/ISUC.2008.75","DOIUrl":"https://doi.org/10.1109/ISUC.2008.75","url":null,"abstract":"Up to now, the method to reduce the ambiguity of phoneme recognition using 2nd-order Markov chain model of phonemes, has been proposed and has been evaluated by phonem lattice simulated and limited to substitution error. However, the method will be necessary to demonstrate the effectiveness for the phoneme candidate lattice obtained by actual speech recognition devices. This paper deals with recurrent neural networks(RNN) which are well- suited for natural language processing of speech recognition, specially for phoneme recognition. The ability of these networks has been investigated by phoneme recognition experiments using a number of Japanese words uttered by a native male speaker in a quiet environment. A method to detect the locations of devoicing vowels using the short- time average energy has been also proposed, and evaluated. Form results of the experiments, it is shown that recognition rates achieved with RNN are higher than those obtained with conventional non-recurrent neural networks, and that the method to detect the locations of devoicing vowels is useful.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"221 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125056063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：