Multidirectional Associative Optimization of Function-Specific Word Representations

Daniela Gerz, Ivan Vulić, Marek Rei, Roi Reichart, Anna Korhonen
2020 Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   unpublished
We present a neural framework for learning associations between interrelated groups of words such as the ones found in Subject-Verb-Object (SVO) structures. Our model induces a joint function-specific word vector space, where vectors of e.g. plausible SVO compositions lie close together. The model retains information about word group membership even in the joint space, and can thereby effectively be applied to a number of tasks reasoning over the SVO structure. We show the robustness and
more » ... bustness and versatility of the proposed framework by reporting state-of-the-art results on the tasks of estimating selectional preference and event similarity. The results indicate that the combinations of representations learned with our task-independent model outperform task-specific architectures from prior work, while reducing the number of parameters by up to 95%.
doi:10.18653/v1/2020.acl-main.257 fatcat:5brp34hl5jfzpgi4ss2d7evwma