Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19-25, 2017 3995-4001 2017 [Refereed]
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]
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...
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...
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]
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 ...
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...
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]
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015 2243-2248 2015 [Refereed]
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]
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 ...
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...
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]
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]
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...
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]
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]
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 ...
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]
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]
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2011, San Francisco, CA, USA, September 25-30, 2011 1540-1547 2011 [Refereed]
INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011 1325-1328 2011 [Refereed]
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]
Affective Computing and Intelligent Interaction - Fourth International Conference, ACII 2011, Memphis, TN, USA, October 9-12, 2011, Proceedings, Part II 22-30 2011 [Refereed]
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...
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...
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]
19th IEEE International Conference on Robot and Human Interactive Communication, Viareggio, Italy, RO-MAN, 2010, September 13-15, 2010 234-239 2010 [Refereed]
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]
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]
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]
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]
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]
INTERSPEECH 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 6-10, 2009 2731-2734 2009 [Refereed]
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...
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...
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]
The 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2008, Munich, Germany, August 1-3, 2008 47-52 2008 [Refereed]
Proceedings of the 10th International Conference on Multimodal Interfaces, ICMI 2008, Chania, Crete, Greece, October 20-22, 2008 293-296 2008 [Refereed]
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 ...
Proceedings of the 12th International Conference on Intelligent User Interfaces, IUI 2007, Honolulu, Hawaii, USA, January 28-31, 2007 333-336 2007 [Refereed]
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]
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...
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]
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]
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]
COLING 2004, 20th International Conference on Computational Linguistics, Proceedings of the Conference, 23-27 August 2004, Geneva, Switzerland 2004 [Refereed]
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...
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．
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
