An Embarrassingly Easy but Strong Baseline for Nested Named Entity Recognition

TL;DR

This paper introduces a simple CNN-based approach to model spatial relations in span-based nested NER, outperforming recent methods and emphasizing the importance of consistent tokenization for fair comparison.

Contribution

The paper presents a straightforward CNN model that effectively captures spatial relations in span-based nested NER, improving performance over existing methods.

Findings

CNN modeling of spatial relations improves nested NER accuracy

Using CNN helps find more nested entities

Preprocessing scripts standardize dataset tokenization

Abstract

Named entity recognition (NER) is the task to detect and classify the entity spans in the text. When entity spans overlap between each other, this problem is named as nested NER. Span-based methods have been widely used to tackle the nested NER. Most of these methods will get a score $n \times n$ matrix, where $n$ means the length of sentence, and each entry corresponds to a span. However, previous work ignores spatial relations in the score matrix. In this paper, we propose using Convolutional Neural Network (CNN) to model these spatial relations in the score matrix. Despite being simple, experiments in three commonly used nested NER datasets show that our model surpasses several recently proposed methods with the same pre-trained encoders. Further analysis shows that using CNN can help the model find more nested entities. Besides, we found that different papers used different sentence tokenizations for the three nested NER datasets, which will influence the comparison. Thus, we release a pre-processing script to facilitate future comparison.