%0 Conference Proceedings %T Integrating Higher-Level Semantics into Robust Biomedical Name Representations %A Fivez, Pieter %A Suster, Simon %A Daelemans, Walter %Y Holderness, Eben %Y Jimeno Yepes, Antonio %Y Lavelli, Alberto %Y Minard, Anne-Lyse %Y Pustejovsky, James %Y Rinaldi, Fabio %S Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis %D 2021 %8 April %I Association for Computational Linguistics %C online %F fivez-etal-2021-integrating %X Neural encoders of biomedical names are typically considered robust if representations can be effectively exploited for various downstream NLP tasks. To achieve this, encoders need to model domain-specific biomedical semantics while rivaling the universal applicability of pretrained self-supervised representations. Previous work on robust representations has focused on learning low-level distinctions between names of fine-grained biomedical concepts. These fine-grained concepts can also be clustered together to reflect higher-level, more general semantic distinctions, such as grouping the names nettle sting and tick-borne fever together under the description puncture wound of skin. It has not yet been empirically confirmed that training biomedical name encoders on fine-grained distinctions automatically leads to bottom-up encoding of such higher-level semantics. In this paper, we show that this bottom-up effect exists, but that it is still relatively limited. As a solution, we propose a scalable multi-task training regime for biomedical name encoders which can also learn robust representations using only higher-level semantic classes. These representations can generalise both bottom-up as well as top-down among various semantic hierarchies. Moreover, we show how they can be used out-of-the-box for improved unsupervised detection of hypernyms, while retaining robust performance on various semantic relatedness benchmarks. %U https://aclanthology.org/2021.louhi-1.6 %P 49-58