Sequence Generation with Label Augmentation for Relation Extraction

Bo Li, Dingyao Yu, Wei Ye, Jinglei Zhang, Shikun Zhang

Abstract: Sequence generation demonstrates promising performance in recent information extraction efforts, by incorporating large-scale pre-trained Seq2Seq models. This paper investigates the merits of employing sequence generation in relation extraction, finding that with relation names or synonyms as generation targets, their textual semantics and the correlation (in terms of word sequence pattern) among them affect model performance. We then propose \textbf{R}elation \textbf{E}xtraction with \textbf{L}abel \textbf{A}ugmentation (\texttt{RELA}), a Seq2Seq model with automatic label augmentation for RE. By saying label augmentation, we mean prod semantically synonyms for each relation name as the generation target. Besides, we present an in-depth analysis of the Seq2Seq model's behavior when dealing with RE. Experimental results show that \texttt{RELA} achieves competitive results compared with previous methods on four RE datasets \footnote{Code is available at https://github.com/pkuserc/RELA}.