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.
|Title of host publication||Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics|
|Editors||Anna Korhonen, David Traum, Lluís Màrquez|
|Place of Publication||Florence, Italy|
|Publisher||Association for Computational Linguistics|
|Number of pages||11|
|Publication status||Published - Jul 2019|
|Event||Annual Meeting of the Association for Computational Linguistics (57th : 2019) - Florence, Italy|
Duration: 28 Jul 2019 → 2 Aug 2019
|Conference||Annual Meeting of the Association for Computational Linguistics (57th : 2019)|
|Period||28/07/19 → 2/08/19|
Bibliographical noteCopyright 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.
Hosseini, M. J., Cohen, S. B., Johnson, M., & Steedman, M. (2019). Duality of link prediction and entailment graph induction. In A. Korhonen, D. Traum, & L. Màrquez (Eds.), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 4736-4746). Florence, Italy: Association for Computational Linguistics. https://doi.org/10.18653/v1/P19-1468