TY - GEN
T1 - Duality of link prediction and entailment graph induction
AU - Hosseini, Mohammad Javad
AU - Cohen, Shay B.
AU - Johnson, Mark
AU - Steedman, Mark
N1 - Copyright the Publisher 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.
PY - 2019/7
Y1 - 2019/7
N2 - Link prediction and entailment graph induction are often treated as different problems. In this paper, we show that these two problems are actually complementary. We train a link prediction model on a knowledge graph of assertions extracted from raw text. We propose an entailment score that exploits the new facts discovered by the link prediction model, and then form entailment graphs between relations. We further use the learned entailments to predict improved link prediction scores. Our results show that the two tasks can benefit from each other. The new entailment score outperforms prior state-of-the-art results on a standard entialment dataset and the new link prediction scores show improvements over the raw link prediction scores.
AB - Link prediction and entailment graph induction are often treated as different problems. In this paper, we show that these two problems are actually complementary. We train a link prediction model on a knowledge graph of assertions extracted from raw text. We propose an entailment score that exploits the new facts discovered by the link prediction model, and then form entailment graphs between relations. We further use the learned entailments to predict improved link prediction scores. Our results show that the two tasks can benefit from each other. The new entailment score outperforms prior state-of-the-art results on a standard entialment dataset and the new link prediction scores show improvements over the raw link prediction scores.
UR - http://www.scopus.com/inward/record.url?scp=85084090774&partnerID=8YFLogxK
U2 - 10.18653/v1/P19-1468
DO - 10.18653/v1/P19-1468
M3 - Conference proceeding contribution
T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
SP - 4736
EP - 4746
BT - Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
A2 - Korhonen, Anna
A2 - Traum, David
A2 - Màrquez, Lluís
PB - Association for Computational Linguistics
CY - Florence, Italy
T2 - Annual Meeting of the Association for Computational Linguistics (57th : 2019)
Y2 - 28 July 2019 through 2 August 2019
ER -