Entity and Event Extraction from Scratch Using Minimal Training Data

Laura Wendlandt; Steve Wilson; Oana Ignat; Charles Welch; Li Zhang; Mingzhe Wang; Jia Deng; Rada Mihalcea

Entity and Event Extraction from Scratch Using Minimal Training Data

Laura Wendlandt, Steve Wilson, Oana Ignat, Charles Welch, Li Zhang, Mingzhe Wang, Jia Deng, Rada Mihalcea

School of Informatics

Research output: Contribution to conference › Paper › peer-review

Abstract / Description of output

Understanding current world events in real-time involves sifting through newsarticles, tweets, photos, and videos from many different perspectives. The goal ofthe DARPA-funded AIDA project1is to automate much of this process, buildinga knowledge base that can be queried to strategically generate hypotheses aboutdifferent aspects of an event. We are participating in this project as a TA1 team,and we are building the first step of the overall system. Given raw multimodalinput (e.g., text, images, video), our goal is to generate a knowledge graph withentities, events, and relations.

Original language	English
Pages	1-9
Number of pages	9
Publication status	Published - 14 Nov 2018
Event	Text Analysis Conference (TAC) 2018 - Gaithersburg, United States Duration: 13 Nov 2018 → 14 Nov 2018 https://tac.nist.gov/2018/index.html

Workshop

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

Access to Document

https://tac.nist.gov/publications/2018/participant.papers/TAC2018.Michigan.proceedings.pdfLicence: All Rights Reserved

Cite this

@conference{25e004515b854609a31816c40f0e20e1,

title = "Entity and Event Extraction from Scratch Using Minimal Training Data",

abstract = "Understanding current world events in real-time involves sifting through newsarticles, tweets, photos, and videos from many different perspectives. The goal ofthe DARPA-funded AIDA project1is to automate much of this process, buildinga knowledge base that can be queried to strategically generate hypotheses aboutdifferent aspects of an event. We are participating in this project as a TA1 team,and we are building the first step of the overall system. Given raw multimodalinput (e.g., text, images, video), our goal is to generate a knowledge graph withentities, events, and relations.",

author = "Laura Wendlandt and Steve Wilson and Oana Ignat and Charles Welch and Li Zhang and Mingzhe Wang and Jia Deng and Rada Mihalcea",

year = "2018",

month = nov,

day = "14",

language = "English",

pages = "1--9",

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

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

}

Wendlandt, L, Wilson, S, Ignat, O, Welch, C, Zhang, L, Wang, M, Deng, J & Mihalcea, R 2018, 'Entity and Event Extraction from Scratch Using Minimal Training Data', Paper presented at Text Analysis Conference (TAC) 2018, Gaithersburg, United States, 13/11/18 - 14/11/18 pp. 1-9. <https://tac.nist.gov/publications/2018/participant.papers/TAC2018.Michigan.proceedings.pdf>

TY - CONF

T1 - Entity and Event Extraction from Scratch Using Minimal Training Data

AU - Wendlandt, Laura

AU - Wilson, Steve

AU - Ignat, Oana

AU - Welch, Charles

AU - Zhang, Li

AU - Wang, Mingzhe

AU - Deng, Jia

AU - Mihalcea, Rada

PY - 2018/11/14

Y1 - 2018/11/14

N2 - Understanding current world events in real-time involves sifting through newsarticles, tweets, photos, and videos from many different perspectives. The goal ofthe DARPA-funded AIDA project1is to automate much of this process, buildinga knowledge base that can be queried to strategically generate hypotheses aboutdifferent aspects of an event. We are participating in this project as a TA1 team,and we are building the first step of the overall system. Given raw multimodalinput (e.g., text, images, video), our goal is to generate a knowledge graph withentities, events, and relations.

AB - Understanding current world events in real-time involves sifting through newsarticles, tweets, photos, and videos from many different perspectives. The goal ofthe DARPA-funded AIDA project1is to automate much of this process, buildinga knowledge base that can be queried to strategically generate hypotheses aboutdifferent aspects of an event. We are participating in this project as a TA1 team,and we are building the first step of the overall system. Given raw multimodalinput (e.g., text, images, video), our goal is to generate a knowledge graph withentities, events, and relations.

M3 - Paper

SP - 1

EP - 9

T2 - Text Analysis Conference (TAC) 2018

Y2 - 13 November 2018 through 14 November 2018

ER -

Entity and Event Extraction from Scratch Using Minimal Training Data

Abstract / Description of output

Workshop

Access to Document

Fingerprint

Cite this