A joint model for entity boundary detection and entity span recognition

Named entity recognition is a task to extract named entities with predefined entity types. Span classifi-cation is a popular method to support this task. It has the advantage to solve nested structures and make full use of token features in a span. The problem is that exhaustively enumerating and verifying all entity spans suffer from high computational complexity and data imbalance. Furthermore, spans with a high overlapping ratio share the same contextual features in a sentence, which is easy to lead to false positive errors caused by inaccurate entity boundaries. In this paper, we present a model to detect the entity boundaries and predict entity candidates jointly. Instead of labeling tokens, our model makes the predic-tion based on gap representations between words, which avoids the ambiguity when a token has several labels. We also propose a neighborhood span proposal strategy to generate reasonable negative samples for training, which effectively reduces the data imbalance problem. Our model is evaluated on the ACE2005 and GENIA corpora. It achieves performance close to the state-of-the-art in F1 scores of 88.55% and 79.81%, respectively.(c) 2022 The Author(s). Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

This paper presents a model for detecting entity boundaries and predicting entity candidates jointly. The model makes predictions based on gap representations between words, avoiding ambiguity when a token has multiple labels. Additionally, a neighborhood span proposal strategy is proposed to address the issue of data imbalance. The model achieves performance close to the state-of-the-art in ACE2005 and GENIA corpora.