FUNAKOSHI Kotaro

J-GLOBAL         Last updated: Oct 9, 2019 at 20:07
 
Avatar
Name
FUNAKOSHI Kotaro
Affiliation
Kyoto University
Degree
Master of Engineering(Tokyo Institute of Technology)
Research funding number
30839311

Research Interests

 
 

Academic & Professional Experience

 
Apr 2006
 - 
Today
Honda Research Institute Japan. Co., Ltd.
 

Education

 
 
 - 
2002
Tokyo Institute of Technology
 
 
 - 
2000
Faculty of Engineering, Tokyo Institute of Technology
 

Published Papers

 
Image2Height: Self-Height Estimation from a Single-Shot Image
Kei Shimonishi, Tyler Fisher, Hiroaki Kawashima, and Kotaro Funakoshi
The 5th Asian Conference on Pattern Recognition (ACPR)      Nov 2019   [Refereed]
Personality Synthesis Using Non-Humanoid Cues
Sam Lee, Kotaro Funakoshi, Ritsuko Iwai, Takatsune Kumada
The Eleventh Conference on Social Robotics (ICSR)      Nov 2019   [Refereed]
Response Obligation Estimation That Considers Users' Repetitive Utterances Using Knowledge-Guided Random Forest
Kotaro Funakoshi, Ryota Yamagami, Shigeki Sugano, Mikio Nakano
2019 IEEE-RAS International Conference on Humanoid Robots (Humanoids)      Oct 2019   [Refereed]
Audio-Visual SLAM towards Human Tracking and Human-Robot Interaction in Indoor Environments
Aaron Chau, Kouhei Sekiguchi, Aditya Arie Nugraha, Kazuyoshi Yoshii, Kotaro Funakoshi
2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)      Oct 2019   [Refereed]
Toward Mindful Machines: A Wizard-of-Oz Dialogue Study
Kotaro Funakoshi, Masato Komuro
Proceedings of the first IEEE international conference on humanized computing and communication (HCC)      Sep 2019   [Refereed]
Vibrational Artificial Subtle Expressions to Convey System’s Confidence Level to Users
Takanori Komatsu, Kazuki Kobayashi, Seiji Yamada, Kotaro Funakoshi, Miki Nakano
Proceedings of The 33rd Annual Conference of Japanese Society for Artificial Intelligence      Jun 2019   [Refereed]
Dialogue system live competition: identifying problems with dialogue systems through live event
Ryuichiro Higashinaka, Kotaro Funakoshi, Michimasa Inaba, Yuiko Tsunomori, Tetsuro Takahashi, Reina Akama
Proceedings of the Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS)      Apr 2019   [Refereed]
Kotaro Funakoshi, Hideaki Shimazaki, Takatsune Kumada, Hiroshi Tsujino
   Mar 2019   [Refereed]
Ryo Nagata, Tomoya Mizumoto, Yuta Kikuchi, Yoshifumi Kawasaki and Kotaro Funakoshi
2018 The 4th Workshop on Noisy User-generated Text (W-NUT)   39-48   Nov 2018   [Refereed]
Satoru Oshikawa,Tomoaki Nakamura,Takayuki Nagai,Masahide Kaneko,Kotaro Funakoshi,Naoto Iwahashi,Mikio Nakano
27th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2018   288-293   Aug 2018   [Refereed]
Takanori Komatsu,Kazuki Kobayashi,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, CHI 2018, Montreal, QC, Canada, April 21-26, 2018   478   2018   [Refereed]
Yasuhiro Shibasaki,Kotaro Funakoshi,Koichi Shinoda
MultiMedia Modeling - 23rd International Conference, MMM 2017, Reykjavik, Iceland, January 4-6, 2017, Proceedings, Part I   677-689   2017   [Refereed]
Ko Endo,Masaki Aono,Eric Nichols,Kotaro Funakoshi
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19-25, 2017   3995-4001   2017   [Refereed]
Kotaro Funakoshi,Mikio Nakano
Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction, HRI 2017, Vienna, Austria, March 6-9, 2017   119-120   Mar 2017   [Refereed]
Takanori Komatsu,Kazuki Kobayashi,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, Denver, CO, USA, May 06-11, 2017.   3501-3505   2017   [Refereed]
Higashinaka Ryuichiro, Funakoshi Kotaro, Araki Masahiro, Tsukahara Hiroshi, Kobayashi Yuka, Mizukami Masahiro
Journal of Natural Language Processing   23(1) 59-86   2016
In general, there are two types of dialogue systems: the task-oriented dialogue system and the non-task-oriented or chat dialogue system. In recent years, chat dialogue systems have received much attention mainly because of the advances in automat...
Sugiyama Takaaki, Funakoshi Kotaro, Nakano Mikio, Komatani Kazunori
Transactions of the Japanese Society for Artificial Intelligence   31(3) C-FB2_1-9   2016   [Refereed]
When a robot interacts with users in public spaces, it receives various sounds such as surrounding noises and users' voices. And furthermore, the robot needs to interact with multiple people at the same time. If the robot incorrectly determines wh...
Ryuichiro Higashinaka,Kotaro Funakoshi,Yuka Kobayashi,Michimasa Inaba
Proceedings of the Tenth International Conference on Language Resources and Evaluation LREC 2016, Portorož, Slovenia, May 23-28, 2016.      2016   [Refereed]
Kei Wakabayashi,Johane Takeuchi,Kotaro Funakoshi,Mikio Nakano
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, November 1-4, 2016   2144-2152   2016   [Refereed]
Takahiro Kobori,Tomoaki Nakamura,Mikio Nakano,Takayuki Nagai,Naoto Iwahashi,Kotaro Funakoshi,Masahide Kaneko
Advanced Robotics   30(24) 1530-1543   2016   [Refereed]
Kobayashi Kazuki, Funakoshi Kotaro, Komatsu Takanori, Yamada Seiji, Nakano Mikio
Transactions of the Japanese Society for Artificial Intelligence   30(4) 604-612   2015   [Refereed]
In this paper, we describe an investigation into users' experiences of a simple talking robot with back-channel feedbacks that is designed based on an artificial subtle expression (ASE). In the experiments with participants, they are divided into ...
Nakamura Tomoaki, Nagai Takayuki, Funakoshi Kotaro, Taniguchi Tadahiro, Iwahashi Naoto, Kaneko Masahide
Transactions of the Japanese Society for Artificial Intelligence   30(3) 498-509   2015   [Refereed]
Humans develop their concept of an object by classifying it into a category, and acquire language by interacting with others at the same time. Thus, the meaning of a word can be learnt by connecting the recognized word and concept. We consider suc...
Ryuichiro Higashinaka,Kotaro Funakoshi,Masahiro Araki,Hiroshi Tsukahara,Yuka Kobayashi,Masahiro Mizukami
Proceedings of the SIGDIAL 2015 Conference, The 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2-4 September 2015, Prague, Czech Republic   87-95   2015   [Refereed]
Takaaki Sugiyama,Kotaro Funakoshi,Mikio Nakano,Kazunori Komatani
15th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2015, Seoul, South Korea, November 3-5, 2015   166-172   2015   [Refereed]
Ryuichiro Higashinaka,Masahiro Mizukami,Kotaro Funakoshi,Masahiro Araki,Hiroshi Tsukahara,Yuka Kobayashi
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015   2243-2248   2015   [Refereed]
Takanori Komatsu,Rui Prada,Kazuki Kobayashi,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
Proceedings of the 37th Annual Meeting of the Cognitive Science Society, CogSci 2015, Pasadena, California, USA, July 22-25, 2015      2015   [Refereed]
Takanori Komatsu,Array,Kazuki Kobayashi,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems, Seoul, CHI 2015 Extended Abstracts, Republic of Korea, April 18 - 23, 2015   2175-2180   2015   [Refereed]
Attamimi Muhammad, Fadlil Muhammad, Abe Kasumi, Nakamura Tomoaki, Funakoshi Kotaro, Nagai Takayuki
Journal of the Robotics Society of Japan   32(8) 753-764   2014   [Refereed]
The human understanding of things is based on prediction which is made through concepts formed by categorization of their experience. To mimic this mechanism in robots, multimodal categorization, which enables the robot to form concepts, has been ...
Muhammad Attamimi,Muhammad Fadlil,Kasumi Abe,Tomoaki Nakamura,Kotaro Funakoshi,Takayuki Nagai
2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, Chicago, IL, USA, September 14-18, 2014   2194-2201   2014   [Refereed]
Tomoaki Nakamura,Takayuki Nagai,Kotaro Funakoshi,Shogo Nagasaka,Tadahiro Taniguchi,Naoto Iwahashi
2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, Chicago, IL, USA, September 14-18, 2014   600-607   2014   [Refereed]
Casey Kennington,Kotaro Funakoshi,Yuki Takahashi,Mikio Nakano
ACM/IEEE International Conference on Human-Robot Interaction, HRI'14, Bielefeld, Germany, March 3-6, 2014   200-201   2014   [Refereed]
Takanori Komatsu,Kazuki Kobayashi,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
5th Augmented Human International Conference, AH '14, Kobe, Japan, March 7-9, 2014   40:1-40:10   2014   [Refereed]
Terada Kazunori, Yamada Seiji, Komatsu Takanori, Kobayashi Kazuki, Funakoshi Kotaro, Nakano Mikio, Ito Akira
Transactions of the Japanese Society for Artificial Intelligence   28(3) 311-319   2013   [Refereed]
In this paper, h-ASE(hesitation-based Artificial Subtle Expression) as a novel implementation of ASE is described, in which a robot expresses confidence in its advice to a human. Confidence in advice is one of robot's useful internal states, and i...
Takashi Yamauchi,Mikio Nakano,Kotaro Funakoshi
Proceedings of the SIGDIAL 2013 Conference, The 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 22-24 August 2013, SUPELEC, Metz, France   369-371   2013   [Refereed]
Seiji Yamada,Kazunori Terada,Kazuki Kobayashi,Takanori Komatsu,Kotaro Funakoshi,Mikio Nakano
2013 ACM SIGCHI Conference on Human Factors in Computing Systems, CHI '13, Paris, France, April 27 - May 2, 2013, Extended Abstracts   1023-1028   2013   [Refereed]
Xiang Zuo,Taisuke Sumii,Naoto Iwahashi,Mikio Nakano,Kotaro Funakoshi,Natsuki Oka
Speech Communication   55(1) 190-203   2013   [Refereed]
Komatsu Takanori, Kobayashi Kazuki, Yamada Seiji, Funakoshi Kotaro, Nakano Mikio
Transactions of the Japanese Society for Artificial Intelligence   27(5) 263-270   2012
Expressing the confidence level of a system's suggestions by using speech sounds is an important cue to users of the system for perceiving how likely it is for the suggestions to be correct. We assume that expressing confidence levels by using hum...
Kotaro Funakoshi,Mikio Nakano,Takenobu Tokunaga,Ryu Iida
Proceedings of the SIGDIAL 2012 Conference, The 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 5-6 July 2012, Seoul National University, Seoul, South Korea   237-246   2012   [Refereed]
Kazuki Kobayashi,Kotaro Funakoshi,Seiji Yamada,Mikio Nakano,Takanori Komatsu,Yasunori Saito
The 21st IEEE International Symposium on Robot and Human Interactive Communication, IEEE RO-MAN 2012, Paris, France, September 9-13, 2012   215-220   2012   [Refereed]
Takanori Komatsu,Kazuki Kobayashi,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
Proceedings of the 34th Annual Meeting of the Cognitive Science Society, CogSci 2012, Sapporo, Japan, August 1-4, 2012      2012   [Refereed]
Takanori Komatsu,Kazuki Kobayashi,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
CHI Conference on Human Factors in Computing Systems, CHI '12, Extended Abstracts Volume, Austin, TX, USA, May 5-10, 2012   1595-1600   2012   [Refereed]
Ryo Nagata,Kotaro Funakoshi,Tatsuya Kitamura,Mikio Nakano
IEICE Transactions   95-D(11) 2658-2663   2012   [Refereed]
Kazunori Komatani,Mikio Nakano,Masaki Katsumaru,Kotaro Funakoshi,Tetsuya Ogata,Hiroshi G. Okuno
IEICE Transactions   95-D(9) 2298-2307   2012   [Refereed]
Takaya Araki,Tomoaki Nakamura,Takayuki Nagai,Kotaro Funakoshi,Mikio Nakano,Naoto Iwahashi
Advanced Robotics   26(17) 1995-2020   2012   [Refereed]
Funakoshi Kotaro, Kobayashi Kazuki, Nakano Mikio, Komatsu Takanori, Yamada Seiji
Transactions of the Japanese Society for Artificial Intelligence   26(2) 353-365   2011
We argue that task-oriented spoken dialogue systems or communication robots do not need to quickly respond verbally as long as they quickly respond non-verbally by showing their internal states by using an artificial subtle expression. This paper ...
Ryo Nagata,Toshiaki Marueki,Kotaro Funakoshi,Tatsuya Kitamura,Mikio Nakano
ISCA International Workshop on Speech and Language Technology in Education, SLaTE 2011, Venice, Italy, August 24-26, 2011   81-84   2011   [Refereed]
Mikio Nakano,Shun Sato,Kazunori Komatani,Kyoko Matsuyama,Kotaro Funakoshi,Hiroshi G. Okuno
Proceedings of the SIGDIAL 2011 Conference, The 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue, June 17-18, 2011, Oregon Science & Health University, Portland, Oregon, USA   18-29   2011   [Refereed]
Kazuki Kobayashi,Kotaro Funakoshi,Seiji Yamada,Mikio Nakano,Takanori Komatsu,Yasunori Saito
20th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2011, Atlanta, Georgia, USA, July 31 - August 3, 2011   181-186   2011   [Refereed]
Takaya Araki,Tomoaki Nakamura,Takayuki Nagai,Kotaro Funakoshi,Mikio Nakano,Naoto Iwahashi
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2011, San Francisco, CA, USA, September 25-30, 2011   1540-1547   2011   [Refereed]
Ryo Taguchi,Yuji Yamada,Koosuke Hattori,Taizo Umezaki,Masahiro Hoguro,Naoto Iwahashi,Kotaro Funakoshi,Mikio Nakano
INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011   1325-1328   2011   [Refereed]
Kotaro Funakoshi,Tomoya Mizumoto,Ryo Nagata,Mikio Nakano
Proceedings of the 6th International Conference on Human Robot Interaction, HRI 2011, Lausanne, Switzerland, March 6-9, 2011   141-142   2011   [Refereed]
Takanori Komatsu,Seiji Yamada,Kazuki Kobayashi,Kotaro Funakoshi,Mikio Nakano
Proceedings of the International Conference on Human Factors in Computing Systems, CHI 2011, Extended Abstracts Volume, Vancouver, BC, Canada, May 7-12, 2011   1249-1254   2011   [Refereed]
Takanori Komatsu,Seiji Yamada,Kazuki Kobayashi,Kotaro Funakoshi,Mikio Nakano
Affective Computing and Intelligent Interaction - Fourth International Conference, ACII 2011, Memphis, TN, USA, October 9-12, 2011, Proceedings, Part II   22-30   2011   [Refereed]
Mikio Nakano,Yuji Hasegawa,Kotaro Funakoshi,Johane Takeuchi,Toyotaka Torii,Kazuhiro Nakadai,Naoyuki Kanda,Kazunori Komatani,Array,Array
Knowl.-Based Syst.   24(2) 248-256   2011   [Refereed]
KATSUMARU Masaki, NAKANO Mikio, KOMATANI Kazunori, FUNAKOSHI Kotaro, TSUJINO Hiroshi, OGATA Tetsuya, OKUNO Hiroshi G.
The IEICE transactions on information and systems   93(6) 879-888   Jun 2010
本論文では,音声対話システムにおいて,複数の言語モデルと複数の言語理解モデルを用いることで,高精度な音声理解を行う手法について述べる.ユーザの発話によって適した言語モデル・言語理解モデルの組合せは異なることから,単一の音声理解方式で様々な発話に対して高精度な音声理解を実現することは難しい.そこで本論文では,まず,複数の言語モデルと言語理解モデルを用いて複数の理解結果を得ることで,理解結果の候補を得る.次に,得られた複数の理解結果に対して,ロジスティック回帰に基づき発話単位の信頼度を付与し,...
FUNAKOSHI Kotaro, KIMURA Noriyuki, NAKANO Mikio, IWAHASHI Naoto
The IEICE transactions on information and systems   93(5) 610-620   May 2010
本論文では,少数の教示発話から,ユーザが任意に決めた物体や場所の名称をロボットが学習し識別するための手法を提案する.高齢者や児童も含めたユーザの使いやすさを高めるためには,語彙や言い回しに関する制限を課さないことが重要である.また,背景雑音などによって生じる誤認識に対して頑健でなければならない.そこで提案手法では,大語彙連続音声認識を用いて入力音声を認識し,複数の認識候補(N-best)に対しbag-of-wordsモデルに基づくトピック分類を適用することで,語彙や言い回しの制限を無くし,...
Taguchi Ryo, Iwahashi Naoto, Funakoshi Kotaro, Nakano Mikio, Nose Takashi, Nitta Tsuneo
Transactions of the Japanese Society for Artificial Intelligence   25(4) 549-559   2010
This paper proposes a method for the unsupervised learning of lexicons from pairs of a spoken utterance and an object as its meaning under the condition that any priori linguistic knowledge other than acoustic models of Japanese phonemes is not us...
Komatsu Takanori, Yamada Seiji, Kobayashi Kazuki, Funakoshi Kotaro, Nakano Mikio
Transactions of the Japanese Society for Artificial Intelligence   25(6) 733-741   2010
We describe artificial subtle expressions (ASEs) as intuitive notification methodology for artificial agents especially in order to convey their internal states for users. We prepared two types of audio ASEs; one is a flat artificial sound (flat A...
Xiang Zuo,Taisuke Sumii,Naoto Iwahashi,Kotaro Funakoshi,Mikio Nakano,Natsuki Oka
2010 IEEE Spoken Language Technology Workshop, SLT 2010, Berkeley, California, USA, December 12-15, 2010   360-365   2010   [Refereed]
Kotaro Funakoshi,Mikio Nakano,Kazuki Kobayashi,Takanori Komatsu,Seiji Yamada
Proceedings of the SIGDIAL 2010 Conference, The 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 24-15 September 2010, Tokyo, Japan   176-184   2010   [Refereed]
Xiang Zuo,Naoto Iwahashi,Ryo Taguchi,Kotaro Funakoshi,Mikio Nakano,Shigeki Matsuda,Komei Sugiura,Natsuki Oka
19th IEEE International Conference on Robot and Human Interactive Communication, Viareggio, Italy, RO-MAN, 2010, September 13-15, 2010   608-613   2010   [Refereed]
Anja Austermann,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
19th IEEE International Conference on Robot and Human Interactive Communication, Viareggio, Italy, RO-MAN, 2010, September 13-15, 2010   234-239   2010   [Refereed]
Hiromi Narimatsu,Mikio Nakano,Kotaro Funakoshi
Spoken Dialogue Systems for Ambient Environments - Second International Workshop on Spoken Dialogue Systems Technology, IWSDS 2010, Gotemba, Shizuoka, Japan, October 1-2, 2010. Proceedings   182-187   2010   [Refereed]
Muhammad Attamimi,Akira Mizutani,Tomoaki Nakamura,Takayuki Nagai,Kotaro Funakoshi,Mikio Nakano
2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, October 18-22, 2010, Taipei, Taiwan   4560-4565   2010   [Refereed]
Anja Austermann,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
INTERSPEECH 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010   2506-2509   2010   [Refereed]
Xiang Zuo,Naoto Iwahashi,Ryo Taguchi,Shigeki Matsuda,Komei Sugiura,Kotaro Funakoshi,Mikio Nakano,Natsuki Oka
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010, 14-19 March 2010, Sheraton Dallas Hotel, Dallas, Texas, USA   2458-2461   2010   [Refereed]
Anja Austermann,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
Proceedings of the 5th ACM/IEEE International Conference on Human Robot Interaction, HRI 2010, Osaka, Japan, March 2-5, 2010   73-74   2010   [Refereed]
Kazunori Komatani,Masaki Katsumaru,Mikio Nakano,Kotaro Funakoshi,Tetsuya Ogata,Hiroshi G. Okuno
COLING 2010, 23rd International Conference on Computational Linguistics, Posters Volume, 23-27 August 2010, Beijing, China   579-587   2010   [Refereed]
Anja Austermann,Seiji Yamada,Kotaro Funakoshi,Mikio Nakano
Proceedings of the 28th International Conference on Human Factors in Computing Systems, CHI 2010, Extended Abstracts Volume, Atlanta, Georgia, USA, April 10-15, 2010   3727-3732   2010   [Refereed]
Takanori Komatsu,Seiji Yamada,Kazuki Kobayashi,Kotaro Funakoshi,Mikio Nakano
Proceedings of the 28th International Conference on Human Factors in Computing Systems, CHI 2010, Atlanta, Georgia, USA, April 10-15, 2010   1941-1944   2010   [Refereed]
Mikio Nakano,Naoto Iwahashi,Takayuki Nagai,Taisuke Sumii,Xiang Zuo,Ryo Taguchi,Takashi Nose,Akira Mizutani,Tomoaki Nakamura,Muhanmad Attamim,Hiromi Narimatsu,Kotaro Funakoshi,Yuji Hasegawa
Dialog with Robots, Papers from the 2010 AAAI Fall Symposium, Arlington, Virginia, USA, November 11-13, 2010      2010   [Refereed]
FUNAKOSHI Kotaro, KOBAYASHI Kazuki, NAKANO Mikio, YAMADA Seiji, KITAMURA Yasuhiko, TSUJINO Hiroshi
The IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences (Japanese edition) A   92(11) 818-827   Nov 2009
音声対話エージェントとユーザ間の対話において,円滑なコミュニケーションの成立が難しく,ユーザが快適にシステムを利用できない問題がある.特に発話の衝突に起因する話者交替の失敗が問題の主要な要因となっている.これに対し,本論文では,エージェントが対話中に明滅光源を用いて内部状態を表出することで発話の衝突を抑制し,円滑なコミュニケーションを実現する手法を提案する.実験では,胸部に取り付けられた発光ダイオードを用いて内部状態を表出する音声対話ロボットを実装し,ユーザと簡単な対話であるしりとりを行わ...
Masaki Katsumaru,Mikio Nakano,Kazunori Komatani,Kotaro Funakoshi,Tetsuya Ogata,Hiroshi G. Okuno
Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings, May 31 - June 5, 2009, Boulder, Colorado, USA, Short Papers   133-136   2009   [Refereed]
Masaki Katsumaru,Mikio Nakano,Kazunori Komatani,Kotaro Funakoshi,Tetsuya Ogata,Hiroshi G. Okuno
INTERSPEECH 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 6-10, 2009   2735-2738   2009   [Refereed]
Ryo Taguchi,Naoto Iwahashi,Takashi Nose,Kotaro Funakoshi,Mikio Nakano
INTERSPEECH 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 6-10, 2009   2731-2734   2009   [Refereed]
Kotaro Funakoshi,Philipp Spanger,Mikio Nakano,Takenobu Tokunaga
ENLG 2009 - Proceedings of the 12th European Workshop on Natural Language Generation, March 30-31, 2009, Athens, Greece   191-194   2009   [Refereed]
福林雄一朗, 駒谷 和範, 中野 幹生, 船越 孝太郎, 辻野 広司, 尾形 哲也, 奥乃 博
情報処理学会論文誌   49(8) 2762-2772   Aug 2008
音声対話システムの開発の初期段階において,言語理解部は,(i) 構築が容易,(ii)様々な表現に対して頑健という2条件を満たす必要がある.本論文では,大量のコーパス収集や人手での詳細な言語理解ルールの記述を行うことなしに,簡単に言語理解部を構築する(ラピッドプロトタイピング)手法について述べる.本手法では,音声認識誤りを含む入力に対して,Weighted Finite State Transducer(WFST)により言語理解結果を出力する.この際の重みは複数種類を定義したうえで,学習デー...
FUNAKOSHI Kotaro, NAKANO Mikio, HASEGAWA Yuji, TSUJINO Hiroshi
Transactions of the Japanese Society for Artificial Intelligence   23(6) 437-446   2008
Natural language interfaces are expected to come into practical use in many situations. It is, however, not practical to expect to achieve a universal interface because language use is so diverse. To that end, not only advancements in speech and l...
Mikio Nakano,Kotaro Funakoshi,Yuji Hasegawa,Hiroshi Tsujino
Proceedings of the SIGDIAL 2008 Workshop, The 9th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 19-20 June 2008, Ohio State University, Columbus, Ohio, USA   88-91   2008   [Refereed]
Kazuki Kobayashi,Kotaro Funakoshi,Seiji Yamada,Mikio Nakano,Yasuhiko Kitamura,Hiroshi Tsujino
The 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2008, Munich, Germany, August 1-3, 2008   47-52   2008   [Refereed]
Yuichiro Fukubayashi,Kazunori Komatani,Mikio Nakano,Kotaro Funakoshi,Hiroshi Tsujino,Tetsuya Ogata,Hiroshi G. Okuno
Third International Joint Conference on Natural Language Processing, IJCNLP 2008, Hyderabad, India, January 7-12, 2008   210-216   2008   [Refereed]
Kotaro Funakoshi,Kazuki Kobayashi,Mikio Nakano,Seiji Yamada,Yasuhiko Kitamura,Hiroshi Tsujino
Proceedings of the 10th International Conference on Multimodal Interfaces, ICMI 2008, Chania, Crete, Greece, October 20-22, 2008   293-296   2008   [Refereed]
FUNAKOSHI KOTARO, WATANABE SATORU, TOKUNAGA TAKENOBU
Journal of Natural Language Processing   14(1) 87-110   2007
Referring expressions are the linguistic representations that identify the referent among objects. Past work of generating referring expressions mainly utilized attributes of objects and binary relations between objects. However, such an approach ...
Yoshitaka Nishimura,Shinichiro Minotsu,Hiroshi Dohi,Mitsuru Ishizuka,Mikio Nakano,Kotaro Funakoshi,Johane Takeuchi,Yuji Hasegawa,Hiroshi Tsujino
Proceedings of the 12th International Conference on Intelligent User Interfaces, IUI 2007, Honolulu, Hawaii, USA, January 28-31, 2007   333-336   2007   [Refereed]
Kotaro Funakoshi,Mikio Nakano,Toyotaka Torii,Yuji Hasegawa,Hiroshi Tsujino,Noriyuki Kimura,Naoto Iwahashi
2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, October 29 - November 2, 2007, Sheraton Hotel and Marina, San Diego, California, USA   1435-1440   2007   [Refereed]
FUNAKOSHI KOTARO, WATANABE SATORU, KURIYAMA NAOKO, TOKUNAGA TAKENOBU
Journal of Natural Language Processing   13(2) 79-97   Apr 2006
Past work of generating referring expressions mainly utilized attributes of objects and binary relations between objects to distinguish the referent from other objects. However, such an approach does not work well when there is no distinctive attr...
Kotaro Funakoshi,Satoru Watanabe,Takenobu Tokunaga
INLG 2006 - Proceedings of the Fourth International Natural Language Generation Conference, July 15-16, 2006, Sydney, Australia   73-80   2006   [Refereed]
Kotaro Funakoshi,Takenobu Tokunaga
EACL 2006, 11st Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, April 3-7, 2006, Trento, Italy      2006   [Refereed]
Kotaro Funakoshi,Takenobu Tokugana
Natural Language Processing - IJCNLP 2005, Second International Joint Conference, Jeju Island, Republic of Korea, October 11-13, 2005 - Companion Volume to the Proceedings of Conference including Posters/Demos and tutorial abstracts      2005   [Refereed]
Kotaro Funakoshi,Satoru Watanabe,Takenobu Tokunaga,Naoko Kuriyama
4th International Conference on Cyberworlds (CW 2005), 23-25 November 2005, Singapore   413-420   2005   [Refereed]
Takenobu Tokugana,Kotaro Funakoshi,Hozumi Tanaka
PRICAI 2004: Trends in Artificial Intelligence, 8th Pacific Rim International Conference on Artificial Intelligence, Auckland, New Zealand, August 9-13, 2004, Proceedings   635-643   2004   [Refereed]
Kotaro Funakoshi,Satoru Watanabe,Naoko Kuriyama,Takenobu Tokunaga
Natural Language Generation, Third International Conference, INLG 2004, Brockenhurst, UK, July 14-16, 2004, Proceedings   51-60   2004   [Refereed]
Kotaro Funakoshi,Satoru Watanabe,Naoko Kuriyama,Takenobu Tokunaga
COLING 2004, 20th International Conference on Computational Linguistics, Proceedings of the Conference, 23-27 August 2004, Geneva, Switzerland      2004   [Refereed]
FUNAKOSHI KOTARO, TOKUNAGA TAKENOBU, TANAKA HOZUMI
Journal of Natural Language Processing   10(4) 33-53   2003
Speech dialog systems need to deal with various kinds of ill-formed speech inputs that appear in natural human-human dialog. Self-correction (or repair) is a particularly problematic phenomenon. Although many methods of dealing with self-correctio...
Kotaro Funakoshi,Takenobu Tokunaga
ISCA Tutorial and Research Workshop (ITRW) on Disfluency in Spontaneous Speech, DiSS '03, Göteborg, Sweden, September 5-8, 2003   55-58   2003   [Refereed]
Processing Japanese Self-correction in Speech Dialog Systems
The 19th International Conference on Computational Linguistics   287-293   2002   [Refereed]

Misc

 
Kotaro Funakoshi
LREC2018 Special Speech Session -Speech Resources Collection in Real-World Situations -   35-39   May 2018   [Invited]
Overview of Dialogue Breakdown Detection Challenge 3
Ryuichiro Higashinaka, Kotaro Funakoshi, Michimasa Inaba, Yuiko Tsunomori , Tetsuro Takahashi, Nobuhiro Kaji
Dialog System Technology Challenges 6      Dec 2017
遠藤 昂, 船越 孝太郎, ニコルズ エリック, 青野 雅樹
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   116(239) 7-12   Oct 2016
東中 竜一郎, 船越 孝太郎, 稲葉 通将, 荒瀬 由紀, 角森 唯子
言語・音声理解と対話処理研究会   78 64-69   Oct 2016
遠藤 昂, 船越 孝太郎, ニコルズ エリック, 青野 雅樹
映像情報メディア学会技術報告 = ITE technical report   40(33) 7-12   Oct 2016
吉井 和輝, Nichols Eric, 船越 孝太郎, 中野 幹生, 青野 雅樹
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   115(516) 1-6   Mar 2016
芝﨑 泰弘, 船越 孝太郎, 篠田 浩一
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   115(516) 119-124   Mar 2016
吉井 和輝, Nichols Eric, 船越 孝太郎, 中野 幹生, 青野 雅樹
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   115(517) 1-6   Mar 2016
芝﨑 泰弘, 船越 孝太郎, 篠田 浩一
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   115(517) 119-124   Mar 2016
Kikkawa Atsushi, iwahashi Naoto, Funakoshi Kotaro, Kunishima Takeo
Proceedings of the IEICE General Conference   2016(2)    Mar 2016
川端 良子, 中野 幹生, 船越 孝太郎
言語・音声理解と対話処理研究会   76 67-72   Feb 2016
東中 竜一郎, 船越 孝太郎
情報処理   57(1) 42-43   Dec 2015   [Invited]
我々は Project Next NLP対話タスクの営みとして,対話システム,特に,雑談を行う対話システムのエラー分析を行った.具体的には,雑談対話コーパスを収集し,対話破綻個所を特定し,これらの対話破綻個所がどのようなシステムのエラーによって引き起こされたかを分析・類型化した.本稿では,我々が本分析に至った背景や得られた知見について解説する.
杉山 貴昭, 船越 孝太郎, 中野 幹生
言語・音声理解と対話処理研究会   75 7-14   Oct 2015
東中 竜一郎, 船越 孝太郎, 小林 優佳
言語・音声理解と対話処理研究会   75 27-32   Oct 2015
Shibasaki Yasuhiro, Funakoshi Kotaro, Shinoda Koichi
情報科学技術フォーラム講演論文集   14(3) 163-166   Aug 2015
杉山 貴昭, 船越 孝太郎, 中野 幹生
人工知能学会全国大会論文集   29 1-4   2015
東中 竜一郎, 船越 孝太郎
言語・音声理解と対話処理研究会   72 45-50   Dec 2014
Sam S. Adams, Itamar Arel, Joscha Bach, Robert Coop, Rob Furlan, Ben Goertzel, J. Storrs Hall, Alexei Samsonovich, Matthias Scheutz, Matthew Schlesinger, Stuart C. Shapiro, John Sowa, Kosuke Shinoda, Ryutaro Ichise, Rafal Rzepka, Atsushi Terao, Kotaro Funakoshi, Hiroyasu Matsushima, Hiroshi Yamakawa, IBM Research, University of Tennessee, Humboldt University of Berlin, University of Tennessee, Singularity University, Novamente LLC:Xiamen University, Institute for Molecular Manufacturing, George Mason University, University of Indiana, South Illinois University, SUNY Buffalo, Vivomind, University of Electro-Communications, National Institute of Informatics, Hokkaido University, Aoyama Gakuin University, Honda Research Institute Japan Co. Ltd., National Institute of Advanced Industrial Science and Technology, Fujitsu Laboratories Ltd.
人工知能 = journal of the Japanese Society for Artificial Intelligence   29(3) 241-257   May 2014
本論文では人間レベルの汎用人工知能(Artificial General Intelligence:以下AGI)の実現に向けたロードマップの概要を述べる.AGI一般に関する議論から始め,実現への現実的な目標および特性と必要条件に関して基本的な定義を行い,AGIが備えるべき能力の起点となる展望(全体図)を示す.具体的には,発達心理学からAGIの主要テーマを導出し,数学的・生理学的・情報処理的観点から実装に必要な知見を得る.AGIの性能評価に適したタスクと環境を同定し,AGIの全体図上のロード...
石川 真也, 船越 孝太郎, 篠田 浩一
人工知能学会全国大会論文集   27    2013
川端 良子, 中野 幹生, 船越 孝太郎
言語・音声理解と対話処理研究会   65 1-6   Jul 2012
山崎 翔太, 中野 幹生, 船越 孝太郎
人工知能学会全国大会論文集   26 1-4   2012
MORI Yasuhiro, NAKAMURA Tomoaki, NAGAI Takayuki, FUNAKOSHI Kotaro, NAKANO Mikio
電気学会研究会資料. IM, 計測研究会   2010(71) 47-52   Dec 2011
ARAKI Takaya, NAKAMURA Tomoaki, NAGAI Takayuki, FUNAKOSHI Kotaro, NAKANO Mikio
電気学会研究会資料. IM, 計測研究会   2010(71) 59-64   Dec 2011
川端 良子, 中野 幹生, 船越 孝太郎
言語・音声理解と対話処理研究会   63 7-12   Oct 2011
船越 孝太郎, 中野 幹生, 徳永 健伸, 飯田 龍
研究報告自然言語処理(NL)   2011(4) 1-11   Jul 2011
対話システムのための,ベイジアンネットワークを用いた参照表現のモデルを提案する.提案モデルは,記述,照応,直示を統一的に扱い,参照表現の理解と生成に用いることができる.本稿では,提案モデルの概要とその利用方法を説明し,様々な参照表現をどのようにベイジアンネットワークとして表現するのかを示す.そして音声対話システムへの統合に向けた議論を行い,関連研究について述べる.A Bayesian network-based model available both for resolution and...
佐藤隼, 中野 幹生, 駒谷 和範, 船越 孝太郎, 奥乃 博
研究報告自然言語処理(NL)   2011(12) 1-8   May 2011
分散型アーキテクチャに基づくマルチドメイン対話システムにおいて,ドメイン選択は非常に重要である.誤ったドメイン選択は対話の進行を著しく阻害するからである.これまでに提案された高精度なドメイン選択法は,特定のタイプのドメインエキスパートでのみ扱える特徴量を使用していた.そこで我々は,2段階ドメイン選択フレームワークを提案した.この方法では,アクティベートされているエキスパートが,入力発話に対し,継続してその発話を扱うか否かを決定する.このプロセスでは,他のエキスパートがアクティベートされる確...
佐藤隼, 中野 幹生, 駒谷 和範, 船越 孝太郎, 奥乃 博
研究報告音声言語情報処理(SLP)   2011(12) 1-8   May 2011
分散型アーキテクチャに基づくマルチドメイン対話システムにおいて,ドメイン選択は非常に重要である.誤ったドメイン選択は対話の進行を著しく阻害するからである.これまでに提案された高精度なドメイン選択法は,特定のタイプのドメインエキスパートでのみ扱える特徴量を使用していた.そこで我々は,2段階ドメイン選択フレームワークを提案した.この方法では,アクティベートされているエキスパートが,入力発話に対し,継続してその発話を扱うか否かを決定する.このプロセスでは,他のエキスパートがアクティベートされる確...
磯部 洋平, 堀内 靖雄, 船越 孝太郎
言語・音声理解と対話処理研究会   61 1-6   Mar 2011
船越 孝太郎, 中野 幹生, 永田 亮
人工知能学会全国大会論文集   25 1-3   2011
船越 孝太郎, 中野 幹生
言語・音声理解と対話処理研究会   60 11-16   Oct 2010
KATSUMARU Masaki, KOMATANI Kazunori, NAKANO Mikio, FUNAKOSHI Kotaro, TSUJINO Hiroshi, OGATA Tetsuya, OKUNO Hiroshi G.
全国大会講演論文集   72(0) 243-244   Mar 2010
成松 宏美, 中野 幹生, 船越 孝太郎, 長谷川 雄二, 辻野 広司
全国大会講演論文集   72(0) 251-252   Mar 2010
MIZUTANI Akira, NAKAMURA Tomoaki, ATTAMIMI Muhammad, NAGAI Takayuki, FUNAKOSHI Kotaro, NAKANO Mikio
全国大会講演論文集   72(0) 581-582   Mar 2010
ATTAMIMI Muhammad, MIZUTANI Akira, NAKAMURA Tomoaki, NAGAI Takayuki, FUNAKOSHI Kotaro, NAKANO Mikio
全国大会講演論文集   72(0) 703-704   Mar 2010
Sumii Taisuke, Iwahashi Naoto, Funakoshi Kotaro, Nakano Mikio, Oka Natsuki
Proceedings of the IEICE General Conference   2010(1)    Mar 2010
磯部 洋平, 堀内 靖雄, 船越 孝太郎
言語・音声理解と対話処理研究会   58 1-6   Feb 2010
KATSUMARU MASAKI, KOMATANI KAZUNORI, NAKANO MIKIO, FUNAKOSHI KOTARO, TSUJINO HIROSHI, OGATA TETSUYA, OKUNO HIROSHI G.
研究報告音声言語情報処理(SLP)   2010(5) 1-6   Feb 2010
本稿では,少量の学習データでも高精度な音声理解を実現する手法について述べる.学習データが少ない場合,単一の音声理解方式による精度は低い傾向にある.そこで本手法では,まず,複数の言語モデルと言語理解モデルを用いて複数の理解結果を得ることで,対処可能な発話を増やす.次に,得られた複数の理解結果に対して,ロジスティック回帰に基づき発話単位の信頼度を付与し,その信頼度が最も高い理解結果を選択する.ロジスティック回帰には,学習データ増加時の回帰係数の変化量に着目することで,必要最低限の学習データを割...
小林 一樹, 船越 孝太郎, 山田 誠二
人工知能学会全国大会論文集   24 1-4   2010
NARIMATSU HIROMI, NAKANO MIKIO, FUNAKOSHI KOTARO, HASEGAWA YUJI, TSUJINO HIROSHI
研究報告音声言語情報処理(SLP)   2009(16) 1-6   Jul 2009
質問と応答のペアからなるデータベースを利用する質問応答システムの性能は,データベースの内容に依存する.できる限り多くの質問パターンを用意することにより,ユーザの質問のバリエーションに対応できる.本稿では,音声質問応答の初期システムを用いて収集したユーザの質問の中から,データベースに追加すべき質問を検出することにより,質問応答データベースの拡張を支援する方法を提案する.提案手法は,質問応答データベースから作成した言語モデルを用いた音声認識結果と,大語彙統計言語モデルを用いた音声認識結果を併用...
KATSUMARU Masaki, NAKANO Mikio, KOMATANI Kazunori, NARIMATSU Hiromi, FUNAKOSHI Kotaro, TSUJINO Hiroshi, TAKAHASHI Toru, OGATA Tetsuya, OKUNO Hiroshi G.
全国大会講演論文集   71(0) 117-118   Mar 2009
KATSUMARU MASAKI, NAKANO MIKIO, KOMATANI KAZUNORI, NARIMATSU HIROMI, FUNAKOSHI KOTARO, TSUJINO HIROSHI, TAKAHASHI TORU, OGATA TETSUYA, OKUNO HIROSHI G.
IPSJ SIG Notes   2009(10) 45-50   Jan 2009
Optimal language models (LMs) and language understanding (LU) methods for spoken dialogue systems vary depending on available training data or utterances to handle. Finding their optimal combination is difficult because much data and expertise are...
NARIMATSU Hiromi, NAKANO Mikio, FUNAKOSHI Kotaro, HASEGAWA Yuji, TSUJINO Hiroshi
IEICE technical report   108(337) 273-278   Dec 2008
This manuscript reports our effort for facilitating building question-answering functions using RIME-TK, which is a toolkit for dialogue and behavior controller for robots/agents. RIME-TK employs experts, each of which is responsible for executing...
NARIMATSU Hiromi, NAKANO Mikio, FUNAKOSHI Kotaro, HASEGAWA Yuji, TSUJINO Hiroshi
IPSJ SIG Notes   2008(123) 273-278   Dec 2008
This manuscript reports our effort for facilitating building question-answering functions using RIME-TK, which is a toolkit for dialogue and behavior controller for robots/agents. RIME-TK employs experts, each of which is responsible for executing...
NARIMATSU Hiromi, NAKANO Mikio, FUNAKOSHI Kotaro, HASEGAWA Yuji, TSUJINO Hiroshi
IEICE technical report   108(338) 273-278   Dec 2008
This manuscript reports our effort for facilitating building question-answering functions using RIME-TK, which is a toolkit for dialogue and behavior controller for robots/agents. RIME-TK employs experts, each of which is responsible for executing...
中野 幹生, 船越 孝太郎, 長谷川 雄二
言語・音声理解と対話処理研究会   54 21-26   Nov 2008
MINOTSU Shinichiro, NAKANO Mikio, FUNAKOSHI Kotaro, KIMURA Noriyuki, IWAHASHI Naoto, ISHIZUKA Mitsuru, TSUJINO Hiroshi
IPSJ SIG Notes   2008(46) 93-98   May 2008
This paper presents a novel method for classifying audience utterances to recognize intentions in interactive presentation systems. It applies a text classification technique to the set of words that appeared in the n-best recognition outputs of a...
Minotsu Shinichiro, Nakano Mikio, Funakoshi Kotaro, Kimura Noriyuki, Iwahashi Naoto, Ishizuka Mitsuru, Tsujino Hiroshi
IPSJ SIG Notes   2008(46) 93-98   May 2008
This paper presents a novel method for classifying audience utterances to recognize intentions in interactive presentation systems. It applies a text classification technique to the set of words that appeared in the n-best recognition outputs of a...
MINOTSU Shinichiro, NAKANO Mikio, FUNAKOSHI Kotaro, TAKEUCHI Johane, HASEGAWA Yuji, DOHI Hiroshi, ISHIZUKA Mitsuru, TSUJINO Hiroshi
全国大会講演論文集   70(0) 145-146   Mar 2008
船越 孝太郎, 小林 一樹, 中野 幹生
人工知能学会全国大会論文集   22 1-4   2008
中野 幹生, 船越 孝太郎, 伊藤 敏彦
人工知能学会全国大会論文集   22 1-4   2008
Fukubayashi Yuichiro, Komatani Kazunori, Nakano Mikio, Funakoshi Kotaro, Ogata Tetsuya, Okuno Hiroshi G.
情報科学技術レターズ   6 133-134   Aug 2007
FUKUBAYASHI YUICHIRO, KOMATANI KAZUNORI, NAKANO MIKIO, FUNAKOSHI KOTARO, TSUJINO HIROSHI, OGATA TETSUYA, OKUNO HlROSHI G.
IPSJ SIG Notes   2007(47) 43-48   May 2007
Weighted Finite State Transducers (WFST) have become common as language understanding modules in spoken dialogue systems. WFSTs promote robust language understanding by assigning appropriate weights to a sequence of recognized words. However, it i...
FUKUBAYASHI YUICHIRO, KOMATANI KAZUNORI, NAKANO MIKIO, FUNAKOSHI KOTARO, TSUJINO HIROSHI, OGATA TETSUYA, OKUNO HIROSHI G.
IPSJ SIG Notes   2007(47) 43-48   May 2007
Weighted Finite State Transducers (WFST) have become common as language understanding modules in spoken dialogue systems. WFSTs promote robust language understanding by assigning appropriate weights to a sequence of recognized words. However, it i...
木村法幸, 岩橋 直人, 中野 幹生, 船越 孝太郎
FIT2007講演論文集   287-290   2007
船越 孝太郎, 中野 幹生, 長谷川 雄二
人工知能学会全国大会論文集   21 1-4   2007
中野 幹生, 船越 孝太郎, 長谷川 雄二
人工知能学会全国大会論文集   21 1-4   2007
FUNAKOSHI Kotaro, TOKUNAGA Takenobu
IPSJ Magazine   45(10) 1032-1037   Oct 2004   [Invited]
 言い直しは,話し言葉の特徴の1つであり,音声言語処理を困難にする.たとえば,言い直しによって,話速やピッチの変化,単語断片の混入が生じ,正確な音声認識が困難になる.また,文法から逸脱した表現や冗長な表現は,構文・意味解析を困難にする.本稿では,言い直しの言語現象を,その生成メカニズム(言い直し行為)と結果(言い直し表現)の2つの側面から解説する.そして,言い直し表現を実際に処理するための手法を言語処理の観点から紹介し,言い直し処理の現状と将来の展望について述べる.
船越 孝太郎, 鈴木 泰裕, 徳永 健伸
人工知能学会全国大会論文集   17 1-4   2003
FUNAKOSHI Kotaro, TOKUNAGA Takenobu
IPSJ SIG Notes   2002(104) 35-41   Nov 2002
Ill-formedness in speech, such as postposition omission, inversion, and self-correction, is a major obstacle which makes speech dialog difficult. We proposed a method to handle these sources of Japanese ill-formedness in our previous paper. In thi...
FUNAKOSHI KOTARO, TOKUNAGA TAKENOBU, TANAKA HOZUMI
IPSJ SIG Notes   2002(4) 55-62   Jan 2002
Speech dialog systems need to deal with various kinds of ill-formedness of speech inputs which appears in natural human-human dialogs. In particular self-correction (or repair) is one of the most problematic phenomena. There have been many proposa...

Books etc

 
Readings in Japanese Natural Language Processing
Kotaro Funakoshi, Takenobu Tokunaga, Hozumi Tanaka (Part:Contributor, Chapter 8)
CSL Publications   Jul 2016   

Research Grants & Projects

 
-
The Other Research Programs