Duality of Link Prediction and Entailment Graph Induction

Mohammad Javad Hosseini, Shay B. Cohen, Mark Johnson, Mark Steedman


Abstract
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.
Anthology ID:
P19-1468
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4736–4746
Language:
URL:
https://aclanthology.org/P19-1468
DOI:
10.18653/v1/P19-1468
Bibkey:
Cite (ACL):
Mohammad Javad Hosseini, Shay B. Cohen, Mark Johnson, and Mark Steedman. 2019. Duality of Link Prediction and Entailment Graph Induction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4736–4746, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Duality of Link Prediction and Entailment Graph Induction (Hosseini et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/P19-1468.pdf
Code
 mjhosseini/linkpred_entgraph
Data
FIGERYAGO