Weakly-Supervised Questions for Zero-Shot Relation Extraction. (arXiv:2301.09640v1 [cs.CL])

Zero-Shot Relation Extraction (ZRE) is the task of Relation Extraction where
the training and test sets have no shared relation types. This very challenging
domain is a good test of a model’s ability to generalize. Previous approaches
to ZRE reframed relation extraction as Question Answering (QA), allowing for
the use of pre-trained QA models. However, this method required manually
creating gold question templates for each new relation. Here, we do away with
these gold templates and instead learn a model that can generate questions for
unseen relations. Our technique can successfully translate relation
descriptions into relevant questions, which are then leveraged to generate the
correct tail entity. On tail entity extraction, we outperform the previous
state-of-the-art by more than 16 F1 points without using gold question
templates. On the RE-QA dataset where no previous baseline for relation
extraction exists, our proposed algorithm comes within 0.7 F1 points of a
system that uses gold question templates. Our model also outperforms the
state-of-the-art ZRE baselines on the FewRel and WikiZSL datasets, showing that
QA models no longer need template questions to match the performance of models
specifically tailored to the ZRE task. Our implementation is available at
https://github.com/fyshelab/QA-ZRE.