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.
@article{arxiv.2210.06600,
title = {Iterative Document-level Information Extraction via Imitation Learning},
author = {Yunmo Chen and William Gantt and Weiwei Gu and Tongfei Chen and Aaron Steven White and Benjamin Van Durme},
journal= {arXiv preprint arXiv:2210.06600},
year = {2023}
}