GAIA: A multi-media multi-lingual knowledge extraction and hypothesis generation system

Tongtao Zhang; Ananya Subburathinam; Ge Shi; Lifu Huang; Di Lu; Xiaoman Pan; Manling Li; Boliang Zhang; Qingyun Wang; Spencer Whitehead; Heng Ji; Alireza Zareian; Hassan Akbari; Brian Chen; Ruiqi Zhong; Steven Shao; Emily Allaway; Shih-Fu Chang; Kathleen McKeown; Dongyu Li; Xin Huang; Kexuan Sun; Xujun Peng; Ryan Gabbard; Marjorie Freedman; Mayank Kejriwal; Ram Nevatia; Pedro Szekely; T.K. Satish Kumar; Ali Sadeghian; Giacomo Bergami; Sourav Dutta; Miguel Rodriguez; Daisy Zhe Wang

GAIA: A multi-media multi-lingual knowledge extraction and hypothesis generation system

Tongtao Zhang, Ananya Subburathinam, Ge Shi, Lifu Huang, Di Lu, Xiaoman Pan, Manling Li, Boliang Zhang, Qingyun Wang, Spencer Whitehead, Heng Ji, Alireza Zareian, Hassan Akbari, Brian Chen, Ruiqi Zhong, Steven Shao, Emily Allaway, Shih-Fu Chang, Kathleen McKeown, Dongyu LiXin Huang, Kexuan Sun, Xujun Peng, Ryan Gabbard, Marjorie Freedman, Mayank Kejriwal, Ram Nevatia, Pedro Szekely, T.K. Satish Kumar, Ali Sadeghian, Giacomo Bergami, Sourav Dutta, Miguel Rodriguez, Daisy Zhe Wang

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

Abstract

An analyst or a planner seeking a rich, deep understanding of an emergent situation today is faced with a paradox multimodal, multilingual real-time information about most emergent situations is freely available but the entropy implied by the sheer volume and diversity of such information makes the task of understanding a specific situation or finding relevant information an immensely challenging one. To remedy this situation, the Generating Alternative Interpretations for Analysis (GAIA) team at DARPA AIDA program aims for automated solutions that provide an integrated, comprehensive, nuanced, and timely view of emerging events, situations, and trends of interest. GAIA focuses on developing a multihypothesis semantic engine that embodies a novel synthesis of new and existing technologies in multimodal knowledge extraction, semantic integration, knowledge graph generation, and inference.

Original language	English
Title of host publication	Proceedings of the Eleventh Text Analysis Conference
Publisher	National Institute of Standards and Technology (NIST)
Pages	1-22
Number of pages	22
Publication status	Published - 14 Nov 2018
Event	Text Analysis Conference 2018 Workshop - National Institute of Standards and Technology, Gaithersburg, United States Duration: 13 Nov 2018 → 14 Nov 2018 https://tac.nist.gov/2018/workshop/index.html

Workshop

Workshop	Text Analysis Conference 2018 Workshop
Abbreviated title	TAC 2018 Workshop
Country/Territory	United States
City	Gaithersburg
Period	13/11/18 → 14/11/18
Internet address	https://tac.nist.gov/2018/workshop/index.html

Access to Document

https://tac.nist.gov/publications/2018/index.html

Cite this

Zhang, T., Subburathinam, A., Shi, G., Huang, L., Lu, D., Pan, X., Li, M., Zhang, B., Wang, Q., Whitehead, S., Ji, H., Zareian, A., Akbari, H., Chen, B., Zhong, R., Shao, S., Allaway, E., Chang, S.-F., McKeown, K., ... Wang, D. Z. (2018). GAIA: A multi-media multi-lingual knowledge extraction and hypothesis generation system. In Proceedings of the Eleventh Text Analysis Conference (pp. 1-22). National Institute of Standards and Technology (NIST). https://tac.nist.gov/publications/2018/index.html

@inproceedings{30c26664574f438b9ac1928100444aca,

title = "GAIA: A multi-media multi-lingual knowledge extraction and hypothesis generation system",

abstract = "An analyst or a planner seeking a rich, deep understanding of an emergent situation today is faced with a paradox multimodal, multilingual real-time information about most emergent situations is freely available but the entropy implied by the sheer volume and diversity of such information makes the task of understanding a specific situation or finding relevant information an immensely challenging one. To remedy this situation, the Generating Alternative Interpretations for Analysis (GAIA) team at DARPA AIDA program aims for automated solutions that provide an integrated, comprehensive, nuanced, and timely view of emerging events, situations, and trends of interest. GAIA focuses on developing a multihypothesis semantic engine that embodies a novel synthesis of new and existing technologies in multimodal knowledge extraction, semantic integration, knowledge graph generation, and inference.",

author = "Tongtao Zhang and Ananya Subburathinam and Ge Shi and Lifu Huang and Di Lu and Xiaoman Pan and Manling Li and Boliang Zhang and Qingyun Wang and Spencer Whitehead and Heng Ji and Alireza Zareian and Hassan Akbari and Brian Chen and Ruiqi Zhong and Steven Shao and Emily Allaway and Shih-Fu Chang and Kathleen McKeown and Dongyu Li and Xin Huang and Kexuan Sun and Xujun Peng and Ryan Gabbard and Marjorie Freedman and Mayank Kejriwal and Ram Nevatia and Pedro Szekely and Kumar, \{T.K. Satish\} and Ali Sadeghian and Giacomo Bergami and Sourav Dutta and Miguel Rodriguez and Wang, \{Daisy Zhe\}",

year = "2018",

month = nov,

day = "14",

language = "English",

pages = "1--22",

booktitle = "Proceedings of the Eleventh Text Analysis Conference",

publisher = "National Institute of Standards and Technology (NIST)",

note = "Text Analysis Conference 2018 Workshop, TAC 2018 Workshop ; Conference date: 13-11-2018 Through 14-11-2018",

url = "https://tac.nist.gov/2018/workshop/index.html",

}

Zhang, T, Subburathinam, A, Shi, G, Huang, L, Lu, D, Pan, X, Li, M, Zhang, B, Wang, Q, Whitehead, S, Ji, H, Zareian, A, Akbari, H, Chen, B, Zhong, R, Shao, S, Allaway, E, Chang, S-F, McKeown, K, Li, D, Huang, X, Sun, K, Peng, X, Gabbard, R, Freedman, M, Kejriwal, M, Nevatia, R, Szekely, P, Kumar, TKS, Sadeghian, A, Bergami, G, Dutta, S, Rodriguez, M & Wang, DZ 2018, GAIA: A multi-media multi-lingual knowledge extraction and hypothesis generation system. in Proceedings of the Eleventh Text Analysis Conference. National Institute of Standards and Technology (NIST), pp. 1-22, Text Analysis Conference 2018 Workshop, Gaithersburg, Maryland, United States, 13/11/18. <https://tac.nist.gov/publications/2018/index.html>

TY - GEN

T1 - GAIA

T2 - Text Analysis Conference 2018 Workshop

AU - Zhang, Tongtao

AU - Subburathinam, Ananya

AU - Shi, Ge

AU - Huang, Lifu

AU - Lu, Di

AU - Pan, Xiaoman

AU - Li, Manling

AU - Zhang, Boliang

AU - Wang, Qingyun

AU - Whitehead, Spencer

AU - Ji, Heng

AU - Zareian, Alireza

AU - Akbari, Hassan

AU - Chen, Brian

AU - Zhong, Ruiqi

AU - Shao, Steven

AU - Allaway, Emily

AU - Chang, Shih-Fu

AU - McKeown, Kathleen

AU - Li, Dongyu

AU - Huang, Xin

AU - Sun, Kexuan

AU - Peng, Xujun

AU - Gabbard, Ryan

AU - Freedman, Marjorie

AU - Kejriwal, Mayank

AU - Nevatia, Ram

AU - Szekely, Pedro

AU - Kumar, T.K. Satish

AU - Sadeghian, Ali

AU - Bergami, Giacomo

AU - Dutta, Sourav

AU - Rodriguez, Miguel

AU - Wang, Daisy Zhe

PY - 2018/11/14

Y1 - 2018/11/14

N2 - An analyst or a planner seeking a rich, deep understanding of an emergent situation today is faced with a paradox multimodal, multilingual real-time information about most emergent situations is freely available but the entropy implied by the sheer volume and diversity of such information makes the task of understanding a specific situation or finding relevant information an immensely challenging one. To remedy this situation, the Generating Alternative Interpretations for Analysis (GAIA) team at DARPA AIDA program aims for automated solutions that provide an integrated, comprehensive, nuanced, and timely view of emerging events, situations, and trends of interest. GAIA focuses on developing a multihypothesis semantic engine that embodies a novel synthesis of new and existing technologies in multimodal knowledge extraction, semantic integration, knowledge graph generation, and inference.

AB - An analyst or a planner seeking a rich, deep understanding of an emergent situation today is faced with a paradox multimodal, multilingual real-time information about most emergent situations is freely available but the entropy implied by the sheer volume and diversity of such information makes the task of understanding a specific situation or finding relevant information an immensely challenging one. To remedy this situation, the Generating Alternative Interpretations for Analysis (GAIA) team at DARPA AIDA program aims for automated solutions that provide an integrated, comprehensive, nuanced, and timely view of emerging events, situations, and trends of interest. GAIA focuses on developing a multihypothesis semantic engine that embodies a novel synthesis of new and existing technologies in multimodal knowledge extraction, semantic integration, knowledge graph generation, and inference.

M3 - Conference contribution

SP - 1

EP - 22

BT - Proceedings of the Eleventh Text Analysis Conference

PB - National Institute of Standards and Technology (NIST)

Y2 - 13 November 2018 through 14 November 2018

ER -

GAIA: A multi-media multi-lingual knowledge extraction and hypothesis generation system

Abstract

Workshop

Access to Document

Fingerprint

Cite this