Document-Level $N$-ary Relation Extraction with Multiscale Representation Learning

Understand

Most information extraction methods focus on binary relations expressed within single sentences.

• In high-value domains, however, $n$-ary relations are of great demand (e.g., drug-gene-mutation interactions in precision oncology).
• Such relations often involve entity mentions that are far apart in the document, yet existing work on cross-sentence relation extraction is generally confined to small text spans (e.g., three consecutive sentences), which severely limits recall.
• In this paper, we propose a novel multiscale neural architecture for document-level $n$-ary relation extraction.