GraphIE: A Graph-Based Framework for Information Extraction
This addresses the limitation of local dependencies in information extraction systems, offering improvements for tasks like textual, social media, and visual extraction.
The paper tackled the problem of information extraction by modeling non-local and non-sequential dependencies using a graph-based framework, resulting in GraphIE consistently outperforming state-of-the-art sequence tagging models across three different tasks.
Most modern Information Extraction (IE) systems are implemented as sequential taggers and only model local dependencies. Non-local and non-sequential context is, however, a valuable source of information to improve predictions. In this paper, we introduce GraphIE, a framework that operates over a graph representing a broad set of dependencies between textual units (i.e. words or sentences). The algorithm propagates information between connected nodes through graph convolutions, generating a richer representation that can be exploited to improve word-level predictions. Evaluation on three different tasks --- namely textual, social media and visual information extraction --- shows that GraphIE consistently outperforms the state-of-the-art sequence tagging model by a significant margin.