... At the bottom left of the window, the character" Genie&a... more ... At the bottom left of the window, the character" Genie" acts as the user's advisor to play the game, and is introduced as" Djinn". ... and Mitsuru Ishizuka 1< listen agent=" Genie"> 2< heard value="Djinn I hit"> 3< scene agents=" Genie, James"> 4< page ref=" casino-main. ...
In this paper, we present a Transputer-based multiprocessor system “TN-V/T” and a software algori... more In this paper, we present a Transputer-based multiprocessor system “TN-V/T” and a software algorithm running on it for real-time interaction between a user’s visual commands (finger signs) and a synthesized moving human face image. A realistic human face (agent) on a monitor can track the palm position and recognize finger signs of a human user. She/he then changes her/his facial expressions in response to the user’s finger signs in real-time. This agent, named VSA (Visual Software Agent), can be viewed as a prototype of an advanced human interface beyond current Iconic interface. We regard this kind of interactive agent as “visual software robot”. The “TN-VIT (Transputer Network with Visual Interface to Transputers)” is an integrated system suitable for real-time image recognition and synthesis which are core functions to realize the visual software robot. The image synthesis speed of the TN-V/T is about 10 frames per second including finger sign recognition process. Some samples of synthesized images and experimental results are shown.
This paper is organized as follows. We rst introduceour VSA system briey. Then we consider what i... more This paper is organized as follows. We rst introduceour VSA system briey. Then we consider what isa cooperative response in the dialog of guidance tasks.In section 4, we describe a dialog management system(DMS) with a learning module. Experimental resultsshown in section 5 prove the capability and characteristicsof our learning mechanism.
Error-rate performance of a digital FM with differential detection in the presence of both therma... more Error-rate performance of a digital FM with differential detection in the presence of both thermal Gaussian noise and cochannel interference is theoretically analyzed in the fast Rayleigh fading environment encountered in the typical UHF or microwave land mobile radio channels. The temporal correlation of the fades is included in the performance analysis. The error probability is presented by a simple closed form for the important situations where both effects of Gaussian noise and cochannel interference predominate in causing errors. Finally, a comparison with the other detection schemes, e.g., discriminator and coherent detections, is given.
Proceedings of the AAAI Conference on Artificial Intelligence
Latent relational search (LRS) is a novel approach for mapping knowledge across two domains. Give... more Latent relational search (LRS) is a novel approach for mapping knowledge across two domains. Given a source domain knowledge concerning the Moon, "The Moon is a satellite of the Earth," one can form a question {(Moon, Earth), (Ganymede, ?)} to query an LRS engine for new knowledge in the target domain concerning the Ganymede. An LRS engine relies on some supporting sentences such as ``Ganymede is a natural satellite of Jupiter.'' to retrieve and rank "Jupiter" as the first answer. This paper proposes cross-language latent relational search (CLRS) to extend the knowledge mapping capability of LRS from cross-domain knowledge mapping to cross-domain and cross-language knowledge mapping. In CLRS, the supporting sentences for the source pair might be in a different language with that of the target pair. We represent the relation between two entities in an entity pair by lexical patterns of the context surrounding the two entities. We then propose a novel hybri...
Proceedings of the AAAI Conference on Artificial Intelligence
Predicting entailment between two given texts is an important task upon which the performance of ... more Predicting entailment between two given texts is an important task upon which the performance of numerous NLP tasks depend on such as question answering, text summarization, and information extraction. The degree to which two texts are similar has been used extensively as a key feature in much previous work in predicting entailment. However, using similarity scores directly, without proper transformations, results in suboptimal performance. Given a set of lexical similarity measures, we propose a method that jointly learns both (a) a set of non-linear transformation functions for those similarity measures and, (b) the optimal non-linear combination of those transformation functions to predict textual entailment. Our method consistently outperforms numerous baselines, reporting a micro-averaged F-score of 46.48 on the RTE- 7 benchmark dataset. The proposed method is ranked 2-nd among 33 entailment systems participated in RTE-7, demonstrating its competitiveness over numerous other en...
... At the bottom left of the window, the character" Genie&a... more ... At the bottom left of the window, the character" Genie" acts as the user's advisor to play the game, and is introduced as" Djinn". ... and Mitsuru Ishizuka 1< listen agent=" Genie"> 2< heard value="Djinn I hit"> 3< scene agents=" Genie, James"> 4< page ref=" casino-main. ...
In this paper, we present a Transputer-based multiprocessor system “TN-V/T” and a software algori... more In this paper, we present a Transputer-based multiprocessor system “TN-V/T” and a software algorithm running on it for real-time interaction between a user’s visual commands (finger signs) and a synthesized moving human face image. A realistic human face (agent) on a monitor can track the palm position and recognize finger signs of a human user. She/he then changes her/his facial expressions in response to the user’s finger signs in real-time. This agent, named VSA (Visual Software Agent), can be viewed as a prototype of an advanced human interface beyond current Iconic interface. We regard this kind of interactive agent as “visual software robot”. The “TN-VIT (Transputer Network with Visual Interface to Transputers)” is an integrated system suitable for real-time image recognition and synthesis which are core functions to realize the visual software robot. The image synthesis speed of the TN-V/T is about 10 frames per second including finger sign recognition process. Some samples of synthesized images and experimental results are shown.
This paper is organized as follows. We rst introduceour VSA system briey. Then we consider what i... more This paper is organized as follows. We rst introduceour VSA system briey. Then we consider what isa cooperative response in the dialog of guidance tasks.In section 4, we describe a dialog management system(DMS) with a learning module. Experimental resultsshown in section 5 prove the capability and characteristicsof our learning mechanism.
Error-rate performance of a digital FM with differential detection in the presence of both therma... more Error-rate performance of a digital FM with differential detection in the presence of both thermal Gaussian noise and cochannel interference is theoretically analyzed in the fast Rayleigh fading environment encountered in the typical UHF or microwave land mobile radio channels. The temporal correlation of the fades is included in the performance analysis. The error probability is presented by a simple closed form for the important situations where both effects of Gaussian noise and cochannel interference predominate in causing errors. Finally, a comparison with the other detection schemes, e.g., discriminator and coherent detections, is given.
Proceedings of the AAAI Conference on Artificial Intelligence
Latent relational search (LRS) is a novel approach for mapping knowledge across two domains. Give... more Latent relational search (LRS) is a novel approach for mapping knowledge across two domains. Given a source domain knowledge concerning the Moon, "The Moon is a satellite of the Earth," one can form a question {(Moon, Earth), (Ganymede, ?)} to query an LRS engine for new knowledge in the target domain concerning the Ganymede. An LRS engine relies on some supporting sentences such as ``Ganymede is a natural satellite of Jupiter.'' to retrieve and rank "Jupiter" as the first answer. This paper proposes cross-language latent relational search (CLRS) to extend the knowledge mapping capability of LRS from cross-domain knowledge mapping to cross-domain and cross-language knowledge mapping. In CLRS, the supporting sentences for the source pair might be in a different language with that of the target pair. We represent the relation between two entities in an entity pair by lexical patterns of the context surrounding the two entities. We then propose a novel hybri...
Proceedings of the AAAI Conference on Artificial Intelligence
Predicting entailment between two given texts is an important task upon which the performance of ... more Predicting entailment between two given texts is an important task upon which the performance of numerous NLP tasks depend on such as question answering, text summarization, and information extraction. The degree to which two texts are similar has been used extensively as a key feature in much previous work in predicting entailment. However, using similarity scores directly, without proper transformations, results in suboptimal performance. Given a set of lexical similarity measures, we propose a method that jointly learns both (a) a set of non-linear transformation functions for those similarity measures and, (b) the optimal non-linear combination of those transformation functions to predict textual entailment. Our method consistently outperforms numerous baselines, reporting a micro-averaged F-score of 46.48 on the RTE- 7 benchmark dataset. The proposed method is ranked 2-nd among 33 entailment systems participated in RTE-7, demonstrating its competitiveness over numerous other en...
Uploads
Papers by M. Ishizuka