# Merge and Label: A novel neural network architecture for nested NER

arXiv: https://arxiv.org/abs/1907.00464 · HTML: https://mlsanity.com/paper/1907.00464/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2019.

## Built on by (most cited first, 17 of 17)

- [A Unified Generative Framework for Various NER Subtasks](https://mlsanity.com/paper/2106.01223/) (2021)
- [A Sequence-to-Set Network for Nested Named Entity Recognition](https://mlsanity.com/paper/2105.08901/) (2021)
- [Paradigm Shift in Natural Language Processing](https://mlsanity.com/paper/2109.12575/) (2021)
- [A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition](https://mlsanity.com/paper/2106.14373/) (2021)
- [Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks](https://mlsanity.com/paper/2110.05419/) (2021)
- [Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition](https://mlsanity.com/paper/2110.07480/) (2021)
- [Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing](https://mlsanity.com/paper/2203.04665/) (2022)
- [Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder](https://mlsanity.com/paper/2109.04500/) (2021)
- [Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting](https://mlsanity.com/paper/2204.11406/) (2022)
- [Named Entity Recognition in the Style of Object Detection](https://mlsanity.com/paper/2101.11122/) (2021)
- [BoningKnife: Joint Entity Mention Detection and Typing for Nested NER via prior Boundary Knowledge](https://mlsanity.com/paper/2107.09429/) (2021)
- [Effect of depth order on iterative nested named entity recognition models](https://mlsanity.com/paper/2104.01037/) (2021)
- [Semantic Norm Recognition and its application to Portuguese Law](https://mlsanity.com/paper/2203.05425/) (2022)
- [Nested Named Entity Recognition as Holistic Structure Parsing](https://mlsanity.com/paper/2204.08006/) (2022)
- [End-to-End Entity Detection with Proposer and Regressor](https://mlsanity.com/paper/2210.10260/) (2022)
- [Nested Named Entity Recognition from Medical Texts: An Adaptive Shared Network Architecture with Attentive CRF](https://mlsanity.com/paper/2211.04759/) (2022)
- [S2F-NER: Exploring Sequence-to-Forest Generation for Complex Entity Recognition](https://mlsanity.com/paper/2310.18944/) (2023)

## Abstract (arXiv)

Named entity recognition (NER) is one of the best studied tasks in natural language processing. However, most approaches are not capable of handling nested structures which are common in many applications. In this paper we introduce a novel neural network architecture that first merges tokens and/or entities into entities forming nested structures, and then labels each of them independently. Unlike previous work, our merge and label approach predicts real-valued instead of discrete segmentation structures, which allow it to combine word and nested entity embeddings while maintaining differentiability. %which smoothly groups entities into single vectors across multiple levels. We evaluate our approach using the ACE 2005 Corpus, where it achieves state-of-the-art F1 of 74.6, further improved with contextual embeddings (BERT) to 82.4, an overall improvement of close to 8 F1 points over previous approaches trained on the same data. Additionally we compare it against BiLSTM-CRFs, the dominant approach for flat NER structures, demonstrating that its ability to predict nested structures does not impact performance in simpler cases.