Cross-domain Generalization for AMR Parsing
This work addresses cross-domain generalization for AMR parsing, which is an incremental improvement for natural language processing applications.
The paper tackled the problem of domain dependence in Abstract Meaning Representation (AMR) parsing by evaluating five parsers across five domains and identifying distribution shifts as key challenges. It proposed methods to reduce domain divergence, showing superiority on two out-of-domain test sets.
Abstract Meaning Representation (AMR) parsing aims to predict an AMR graph from textual input. Recently, there has been notable growth in AMR parsing performance. However, most existing work focuses on improving the performance in the specific domain, ignoring the potential domain dependence of AMR parsing systems. To address this, we extensively evaluate five representative AMR parsers on five domains and analyze challenges to cross-domain AMR parsing. We observe that challenges to cross-domain AMR parsing mainly arise from the distribution shift of words and AMR concepts. Based on our observation, we investigate two approaches to reduce the domain distribution divergence of text and AMR features, respectively. Experimental results on two out-of-domain test sets show the superiority of our method.