How to Encode Domain Information in Relation Classification

arXiv:2404.13760v1 Announce Type: new
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 …

abstract arxiv classification cs.cl current data datasets domain encode encoding explore information language language models performance setup training training data type