Learning word meanings and grammar for describing everyday activities in smart environments

Muhammad Attamimi; Yuji Ando; Tomoaki Nakamura; Takayuki Nagai; Daichi Mochihashi; Ichiro Kobayashi; Hideki Asoh

doi:10.18653/v1/d15-1269

Learning word meanings and grammar for describing everyday activities in smart environments

Muhammad Attamimi, Yuji Ando, Tomoaki Nakamura, Takayuki Nagai, Daichi Mochihashi, Ichiro Kobayashi, Hideki Asoh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

If intelligent systems are to interact with humans in a natural manner, the ability to describe daily life activities is important. To achieve this, sensing human activities by capturing multimodal information is necessary. In this study, we consider a smart environment for sensing activities with respect to realistic scenarios. We next propose a sentence generation system from observed multimodal information in a bottom up manner using multilayered multimodal latent Dirichlet allocation and Bayesian hidden Markov models. We evaluate the grammar learning and sentence generation as a complete process within a realistic setting. The experimental result reveals the effectiveness of the proposed method.

Original language	English
Title of host publication	Conference Proceedings - EMNLP 2015
Subtitle of host publication	Conference on Empirical Methods in Natural Language Processing
Publisher	Association for Computational Linguistics (ACL)
Pages	2249-2254
Number of pages	6
ISBN (Electronic)	9781941643327
DOIs	https://doi.org/10.18653/v1/d15-1269
Publication status	Published - 2015
Externally published	Yes
Event	Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal Duration: 17 Sept 2015 → 21 Sept 2015

Publication series

Name	Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing

Conference

Conference	Conference on Empirical Methods in Natural Language Processing, EMNLP 2015
Country/Territory	Portugal
City	Lisbon
Period	17/09/15 → 21/09/15

Access to Document

10.18653/v1/d15-1269

Cite this

Attamimi, M., Ando, Y., Nakamura, T., Nagai, T., Mochihashi, D., Kobayashi, I., & Asoh, H. (2015). Learning word meanings and grammar for describing everyday activities in smart environments. In Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing (pp. 2249-2254). (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/d15-1269

Attamimi, Muhammad ; Ando, Yuji ; Nakamura, Tomoaki et al. / Learning word meanings and grammar for describing everyday activities in smart environments. Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), 2015. pp. 2249-2254 (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing).

@inproceedings{00a84d16dbcd454eb78f8294cc29148f,

title = "Learning word meanings and grammar for describing everyday activities in smart environments",

abstract = "If intelligent systems are to interact with humans in a natural manner, the ability to describe daily life activities is important. To achieve this, sensing human activities by capturing multimodal information is necessary. In this study, we consider a smart environment for sensing activities with respect to realistic scenarios. We next propose a sentence generation system from observed multimodal information in a bottom up manner using multilayered multimodal latent Dirichlet allocation and Bayesian hidden Markov models. We evaluate the grammar learning and sentence generation as a complete process within a realistic setting. The experimental result reveals the effectiveness of the proposed method.",

author = "Muhammad Attamimi and Yuji Ando and Tomoaki Nakamura and Takayuki Nagai and Daichi Mochihashi and Ichiro Kobayashi and Hideki Asoh",

note = "Publisher Copyright: {\textcopyright} 2015 Association for Computational Linguistics.; Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 ; Conference date: 17-09-2015 Through 21-09-2015",

year = "2015",

doi = "10.18653/v1/d15-1269",

language = "English",

series = "Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing",

publisher = "Association for Computational Linguistics (ACL)",

pages = "2249--2254",

booktitle = "Conference Proceedings - EMNLP 2015",

address = "United States",

}

Attamimi, M, Ando, Y, Nakamura, T, Nagai, T, Mochihashi, D, Kobayashi, I & Asoh, H 2015, Learning word meanings and grammar for describing everyday activities in smart environments. in Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics (ACL), pp. 2249-2254, Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, 17/09/15. https://doi.org/10.18653/v1/d15-1269

Learning word meanings and grammar for describing everyday activities in smart environments. / Attamimi, Muhammad; Ando, Yuji; Nakamura, Tomoaki et al.
Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), 2015. p. 2249-2254 (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Learning word meanings and grammar for describing everyday activities in smart environments

AU - Attamimi, Muhammad

AU - Ando, Yuji

AU - Nakamura, Tomoaki

AU - Nagai, Takayuki

AU - Mochihashi, Daichi

AU - Kobayashi, Ichiro

AU - Asoh, Hideki

PY - 2015

Y1 - 2015

N2 - If intelligent systems are to interact with humans in a natural manner, the ability to describe daily life activities is important. To achieve this, sensing human activities by capturing multimodal information is necessary. In this study, we consider a smart environment for sensing activities with respect to realistic scenarios. We next propose a sentence generation system from observed multimodal information in a bottom up manner using multilayered multimodal latent Dirichlet allocation and Bayesian hidden Markov models. We evaluate the grammar learning and sentence generation as a complete process within a realistic setting. The experimental result reveals the effectiveness of the proposed method.

AB - If intelligent systems are to interact with humans in a natural manner, the ability to describe daily life activities is important. To achieve this, sensing human activities by capturing multimodal information is necessary. In this study, we consider a smart environment for sensing activities with respect to realistic scenarios. We next propose a sentence generation system from observed multimodal information in a bottom up manner using multilayered multimodal latent Dirichlet allocation and Bayesian hidden Markov models. We evaluate the grammar learning and sentence generation as a complete process within a realistic setting. The experimental result reveals the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84959928537&partnerID=8YFLogxK

U2 - 10.18653/v1/d15-1269

DO - 10.18653/v1/d15-1269

M3 - Conference contribution

AN - SCOPUS:84959928537

T3 - Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing

SP - 2249

EP - 2254

BT - Conference Proceedings - EMNLP 2015

PB - Association for Computational Linguistics (ACL)

T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2015

Y2 - 17 September 2015 through 21 September 2015

ER -

Attamimi M, Ando Y, Nakamura T, Nagai T, Mochihashi D, Kobayashi I et al. Learning word meanings and grammar for describing everyday activities in smart environments. In Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL). 2015. p. 2249-2254. (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing). doi: 10.18653/v1/d15-1269

Learning word meanings and grammar for describing everyday activities in smart environments

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this