%0 Conference Proceedings %T Multivalent Entailment Graphs for Question Answering %A McKenna, Nick %A Guillou, Liane %A Hosseini, Mohammad Javad %A Bijl de Vroe, Sander %A Johnson, Mark %A Steedman, Mark %Y Moens, Marie-Francine %Y Huang, Xuanjing %Y Specia, Lucia %Y Yih, Scott Wen-tau %S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing %D 2021 %8 November %I Association for Computational Linguistics %C Online and Punta Cana, Dominican Republic %F mckenna-etal-2021-multivalent %X Drawing inferences between open-domain natural language predicates is a necessity for true language understanding. There has been much progress in unsupervised learning of entailment graphs for this purpose. We make three contributions: (1) we reinterpret the Distributional Inclusion Hypothesis to model entailment between predicates of different valencies, like DEFEAT(Biden, Trump) entails WIN(Biden); (2) we actualize this theory by learning unsupervised Multivalent Entailment Graphs of open-domain predicates; and (3) we demonstrate the capabilities of these graphs on a novel question answering task. We show that directional entailment is more helpful for inference than non-directional similarity on questions of fine-grained semantics. We also show that drawing on evidence across valencies answers more questions than by using only the same valency evidence. %R 10.18653/v1/2021.emnlp-main.840 %U https://aclanthology.org/2021.emnlp-main.840 %U https://doi.org/10.18653/v1/2021.emnlp-main.840 %P 10758-10768