TY - GEN
T1 - Reasoning about RoboCup soccer narratives
AU - Hajishirzi, Hannaneh
AU - Hockenmaier, Julia
AU - Mueller, Erik T.
AU - Amir, Eyal
PY - 2011
Y1 - 2011
N2 - This paper presents an approach for learning to translate simple narratives, i.e., texts (sequences of sentences) describing dynamic systems, into coherent sequences of events without the need for labeled training data. Our approach incorporates domain knowledge in the form of preconditions and effects of events, and we show that it outperforms state-of-the-art supervised learning systems on the task of reconstructing RoboCup soccer games from their commentaries.
AB - This paper presents an approach for learning to translate simple narratives, i.e., texts (sequences of sentences) describing dynamic systems, into coherent sequences of events without the need for labeled training data. Our approach incorporates domain knowledge in the form of preconditions and effects of events, and we show that it outperforms state-of-the-art supervised learning systems on the task of reconstructing RoboCup soccer games from their commentaries.
UR - https://www.scopus.com/pages/publications/80053163892
UR - https://www.scopus.com/pages/publications/80053163892#tab=citedBy
M3 - Conference contribution
AN - SCOPUS:80053163892
T3 - Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011
SP - 291
EP - 300
BT - Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011
PB - AUAI Press
ER -