TY - GEN
T1 - COSATA
T2 - 2020 System Demonstrations of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020
AU - Jansen, Peter A.
N1 - Publisher Copyright:
© 2020 Association for Computational Linguistics.
PY - 2020
Y1 - 2020
N2 - This work presents COSATA, an intuitive constraint satisfaction solver and interpreted language for knowledge bases of semi-structured tables expressed as text. The stand-alone COSATA solver allows easily expressing complex compositional “inference patterns” for how knowledge from different tables tends to connect to support inference and explanation construction in question answering and other downstream tasks, while including advanced declarative features and the ability to operate over multiple representations of text (words, lemmas, or part-of-speech tags). COSATA also includes a hybrid imperative/declarative interpreted language for expressing simple models through minimally-specified simulations grounded in constraint patterns, helping bridge the gap between question answering, question explanation, and model simulation. The solver and interpreter are released as open source.
AB - This work presents COSATA, an intuitive constraint satisfaction solver and interpreted language for knowledge bases of semi-structured tables expressed as text. The stand-alone COSATA solver allows easily expressing complex compositional “inference patterns” for how knowledge from different tables tends to connect to support inference and explanation construction in question answering and other downstream tasks, while including advanced declarative features and the ability to operate over multiple representations of text (words, lemmas, or part-of-speech tags). COSATA also includes a hybrid imperative/declarative interpreted language for expressing simple models through minimally-specified simulations grounded in constraint patterns, helping bridge the gap between question answering, question explanation, and model simulation. The solver and interpreter are released as open source.
UR - http://www.scopus.com/inward/record.url?scp=85127443475&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127443475&partnerID=8YFLogxK
U2 - 10.18653/v1/2020.emnlp-demos.10
DO - 10.18653/v1/2020.emnlp-demos.10
M3 - Conference contribution
AN - SCOPUS:85127443475
T3 - EMNLP 2020 - Conference on Empirical Methods in Natural Language Processing, Proceedings of Systems Demonstrations
SP - 70
EP - 76
BT - EMNLP 2020 - Conference on Empirical Methods in Natural Language Processing, Proceedings of Systems Demonstrations
A2 - Liu, Qun
A2 - Schlangen, David
PB - Association for Computational Linguistics (ACL)
Y2 - 16 November 2020 through 20 November 2020
ER -