%0 Conference Proceedings %T Iterative Document-level Information Extraction via Imitation Learning %A Chen, Yunmo %A Gantt, William %A Gu, Weiwei %A Chen, Tongfei %A White, Aaron %A Van Durme, Benjamin %Y Vlachos, Andreas %Y Augenstein, Isabelle %S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics %D 2023 %8 May %I Association for Computational Linguistics %C Dubrovnik, Croatia %F chen-etal-2023-iterative %X We present a novel iterative extraction model, IterX, for extracting complex relations, or templates, i.e., N-tuples representing a mapping from named slots to spans of text within a document. Documents may feature zero or more instances of a template of any given type, and the task of template extraction entails identifying the templates in a document and extracting each template’s slot values. Our imitation learning approach casts the problem as a Markov decision process (MDP), and relieves the need to use predefined template orders to train an extractor. It leads to state-of-the-art results on two established benchmarks – 4-ary relation extraction on SciREX and template extraction on MUC-4 – as well as a strong baseline on the new BETTER Granular task. %R 10.18653/v1/2023.eacl-main.136 %U https://aclanthology.org/2023.eacl-main.136 %U https://doi.org/10.18653/v1/2023.eacl-main.136 %P 1858-1874