A dynamic programming algorithm for span-based nested named-entity recognition in O(n^2)

TL;DR

This paper introduces a quadratic-time dynamic programming algorithm for span-based nested named-entity recognition, significantly improving efficiency while maintaining competitive accuracy on standard benchmarks.

Contribution

The paper presents a novel structural constraint that reduces the complexity of nested NER from cubic to quadratic time, matching the non-nested case.

Findings

Achieves quadratic time complexity for nested NER

Performs comparably to existing methods on benchmarks

Reduces computational cost significantly

Abstract

Span-based nested named-entity recognition (NER) has a cubic-time complexity using a variant of the CYK algorithm. We show that by adding a supplementary structural constraint on the search space, nested NER has a quadratic-time complexity, that is the same asymptotic complexity than the non-nested case. The proposed algorithm covers a large part of three standard English benchmarks and delivers comparable experimental results.