CLJul 29, 2021

SeqScore: Addressing Barriers to Reproducible Named Entity Recognition Evaluation

arXiv:2107.14154v3663 citations
Originality Synthesis-oriented
AI Analysis

This addresses reproducibility issues for researchers in natural language processing, though it is incremental as it focuses on improving existing evaluation practices.

The paper tackled the problem of unreproducible evaluation in named entity recognition by proposing simple guidelines and introducing SeqScore, a software package, demonstrating that scoring differences can cause noticeable and statistically significant changes in scores.

To address a looming crisis of unreproducible evaluation for named entity recognition, we propose guidelines and introduce SeqScore, a software package to improve reproducibility. The guidelines we propose are extremely simple and center around transparency regarding how chunks are encoded and scored. We demonstrate that despite the apparent simplicity of NER evaluation, unreported differences in the scoring procedure can result in changes to scores that are both of noticeable magnitude and statistically significant. We describe SeqScore, which addresses many of the issues that cause replication failures.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes