How to Encode Domain Information in Relation Classification
Abstract
Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific, so combining datasets to obtain better performance is non-trivial. We explore a multi-domain training setup for RC, and attempt to improve performance by encoding domain information. Our proposed models improve > 2 Macro-F1 against the baseline setup, and our analysis reveals that not all the labels benefit the same: The classes which occupy a similar space across domains (i.e., their interpretation is close across them, for example "physical") benefit the least, while domain-dependent relations (e.g., "part-of'') improve the most when encoding domain information.
Cite
@article{arxiv.2404.13760,
title = {How to Encode Domain Information in Relation Classification},
author = {Elisa Bassignana and Viggo Unmack Gascou and Frida Nøhr Laustsen and Gustav Kristensen and Marie Haahr Petersen and Rob van der Goot and Barbara Plank},
journal= {arXiv preprint arXiv:2404.13760},
year = {2024}
}
Comments
Accepted at LREC-COLING 2024