TY - GEN
T1 - Eidos, INDRA, & Delphi
T2 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019
AU - Sharp, Rebecca
AU - Pyarelal, Adarsh
AU - Gyori, Benjamin M.
AU - Alcock, Keith
AU - Laparra, Egoitz
AU - Valenzuela-Escarcega, Marco A.
AU - Nagesh, Ajay
AU - Yadav, Vikas
AU - Bachman, John A.
AU - Tang, Zheng
AU - Lent, Heather
AU - Luo, Fan
AU - Paul, Mithun
AU - Bethard, Steven
AU - Barnard, Kobus
AU - Morrison, Clayton T.
AU - Surdeanu, Mihai
N1 - Publisher Copyright:
© 2019 The Association for Computational Linguistics.
PY - 2019
Y1 - 2019
N2 - Building causal models of complicated phenomena such as food insecurity is currently a slow and labor-intensive manual process. In this paper, we introduce an approach that builds executable probabilistic models from raw, free text. The proposed approach is implemented through three systems: Eidos1, INDRA2 and Delphi3. Eidos is an open-domain machine reading system designed to extract causal relations from natural language. It is rule-based, allowing for rapid domain transfer, customizability, and interpretability. INDRA aggregates multiple sources of causal information and performs assembly to create a coherent knowledge base and assess its reliability. This assembled knowledge serves as the starting point for modeling. Delphi is a modeling framework that assembles quantified causal fragments and their contexts into executable probabilistic models that respect the semantics of the original text and can be used to support decision making.
AB - Building causal models of complicated phenomena such as food insecurity is currently a slow and labor-intensive manual process. In this paper, we introduce an approach that builds executable probabilistic models from raw, free text. The proposed approach is implemented through three systems: Eidos1, INDRA2 and Delphi3. Eidos is an open-domain machine reading system designed to extract causal relations from natural language. It is rule-based, allowing for rapid domain transfer, customizability, and interpretability. INDRA aggregates multiple sources of causal information and performs assembly to create a coherent knowledge base and assess its reliability. This assembled knowledge serves as the starting point for modeling. Delphi is a modeling framework that assembles quantified causal fragments and their contexts into executable probabilistic models that respect the semantics of the original text and can be used to support decision making.
UR - https://www.scopus.com/pages/publications/85085638450
UR - https://www.scopus.com/pages/publications/85085638450#tab=citedBy
M3 - Conference contribution
AN - SCOPUS:85085638450
T3 - NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Demonstrations Session
SP - 42
EP - 47
BT - NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
Y2 - 2 June 2019 through 7 June 2019
ER -