Dai Hasegawa's Homepage

Profile
(drag these)

Publications
(click pics)

close

	Dai Hasegawa

	Born on 11 November 1984, Hokkaido, Japan.

	
	AFFILIATE
	DC1
	Language Media Laboratory
	Graduate School of Information Science and Technology
	Hokkaido University
 
	EDUCATION
	4/2007-3/2009, Hokkaido University, Sapporo, Japan,

	Department of Information Science and Technology (Master Degree)
	4/2005-3/2007, Hokkaido University, Sapporo, Japan, Department of Engineering
	4/2000-3/2005, Asahikawa National College of Technology, Asahikawa, Japan

close

Book

Dai Hasegawa, Rafal Rzepka and Kenji Araki:
"Connectives Acquisition in a Humanoid Robot Based on an Inductive Learning Language Acquisition Model",
Humanoid Robots, Edited by Ben Choi, In-Tech, Vienna, Austria, pp.65-82, 2009, ISBN 978-953-7619-44-2.

Paper

Dai Hasegawa, Rafal Rzepka and Kenji Araki:
"Evaluation of Connectives Acquisition in a Humanoid Robot Using Direct Physical Feedback",
Springer-Verlag Lecture Notes in Artificial Intelligence (LNAI) 4830, pp.664-668, Surffers Paradise, Austraria, 2007. pdf

International Conference

Dai Hasegawa, Jonas Sjobergh, Rafal Rzepka and Kenji Araki:
"Automatically Choosing Appropriate Gestures for Jokes",
To appear the Proceedings of the Fifth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-09), San Francisco, USA, October 2009.
Dai Hasegawa, Rafal Rzepka and Kenji Araki:
"Body Movement Verbs Acquisition for a Humanoid Robot Through Physical Interaction with Human",
To appear the Proceedings of the Fifth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-09), San Francisco, USA, October 2009.
Dai Hasegawa, Rafal Rzepka and Kenji Araki:
"Teaching a Humanoid Robot through Physical Feedback: So Easy Even a Five Year Old Could Use It",
To appear the Proceedings of The 19th Intelligent System Symposium FAN2009, Aizu-Wakamatsu, Japan, September 2009.
Keiichi Takamaru, Hideyuki Shibuki, Yasutomo Kimura, Dai Hasegawa, Hokuto Ototake and Kenji Araki:
"Extraction or Political Activity of Assemblyman from Minutes of Municipal Assemblies Using the Plitical Category",
To appear the Proceedings of Conference of the Pacific Association for Computational Linguistics (PACLING2009), Sapporo, Japan, September 2009.
Dai Hasegawa, Jonas Sjobergh, Rafal Rzepka and Kenji Araki:
"Are Body Movements Really Important for Joke Systems? Comparing Different Styles of Joke Performance",
The Proceedings of the First International Workshop on Laughter in Interaction and Body Movement (LIBM'08), pp.8-13, Asahikawa, Japan, June 2008. pdf

国内発表

長谷川大, ジェプカラファウ, 荒木健治:
"ヒューマノイドロボットにおける二項動詞獲得手法の性能評価",
第23回人工知能学会全国大会, 1F2-OS7-4(CD-ROM), 高松, 6/2009.

長谷川大, ラファウジェプカ, 荒木健治:
"ヒューマノイドロボットにおける身体操作を表現するための二項動詞の獲得",
言語処理学会第15回年次大会発表論文集(CD-ROM), P2-9, 鳥取, 3/2009.

長谷川大, 乙武北斗, 木村泰知, 渋木英潔, 高丸圭一, 荒木健治:
"市議会会議録を対象とした概念体系構築へ向けた分析",
第187回自然言語処理研究会, 第187回自然言語処理研究会の研究報告, 2008-NL-187, pp 23-28, 熱海, 9/2008.

長谷川大, ジェプカラファウ, 荒木健治:
"ヒューマノイドロボットを用いた行動教示による接続語獲得手法の性能評価",
第21回人工知能学会全国大会, 1F2-7(CD-ROM), 宮崎, 6/2007.

close


	ADDRESS
	Language Media Laboratory 
	Research Group of Information Media Science and Technology 
	Division of Media and Network Technologies 
	Graduate School of Information Science and Technology 
	Hokkaido University, Kita-ku Kita 14 Nishi 9,
	060-0814 Sapporo, Japan

	TEL/FAX
	TEL:(+81)(11)706-7389
	FAX:(+81)(11)-709-6277 

	E-MAIL ADDRESS
	hasegawadai[at]media.eng.hokudai.ac.jp

close

        I will describe my current research topics and abstracts.

"Connective Acquisition in a Humanoid Robot"
We developed a humanoid robot that can acquire connective meanings through interaction with people. In this system, the user inputs a textual command from keyboard like "raise the right hand and after that raise the left hand". Then the user teaches the robot a proper movement by moving robot's arm directly. Our system acquired 70% connectives of all connectives taught by subjects. It can be also said that the robot partially learned the concept of time.
"Verb Acquisition in a Humanoid Robot"
We proposed a language grounding method that relates verbs which imply body manipulation to motor angle patterns in a humanoid robot to make robots more entertaining. In established methods, verbs are represented by statistical models based on trajectories or motor patterns of a trajector. In our method we use a novel representation model that has six features including both trajector-reference point relationships and the trajector's trajectory. By using this model, some verbs which do not depend on a trajectory, e.g. "move the right hand close to the left hand" are represented more adequately. In our language grounding method a humanoid robot generates abstract verb meanings independent of context. As input, it uses sets of a user input textual command and a motor pattern. The motor pattern is taught using direct physical feedback resembling playing with a child. We implemented the algorithm in a humanoid robot and conducted a verb acquisition experiment. As a result, four problematic verbs, "place-on", "move-close-to", "move-away-from", and "touch-with" were acquired correctly.
"Natural Body Gestures in a Humanoid Robot"
We examined the problem of automatically selecting gestures that are appropriate to use when telling a joke or a short story. Our current application of this is a joke telling humanoid robot that needs to be able to select natural gestures for arbitrary input. The topic is important because humans use body language and gestures, thus socially interactive robots should also be able to do so for more natural interaction. We asked evaluators to assign appropriate gestures from a set of gestures the robot can perform to 50 jokes from a corpus of jokes in Japanese. We then evaluated different methods for automatically selecting gestures on this data. While human inter-agreement was rather low, indicating that this is a fairly difficult task and that some jokes have no obviously fitting gesture, the best method performs on par with humans and clearly outperforms the baseline.
"Local Politics Support System Using NLP"
Now custructing...