# Nested Named Entity Recognition as Holistic Structure Parsing

arXiv: https://arxiv.org/abs/2204.08006 · HTML: https://mlsanity.com/paper/2204.08006/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 17 Apr 2022.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://mlsanity.com/paper/1603.01354/) (2016)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [A Unified MRC Framework for Named Entity Recognition](https://mlsanity.com/paper/1910.11476/) (2019)
- [A Unified Generative Framework for Various NER Subtasks](https://mlsanity.com/paper/2106.01223/) (2021)
- [A General Framework for Information Extraction using Dynamic Span Graphs](https://mlsanity.com/paper/1904.03296/) (2019)
- [Neural Architectures for Nested NER through Linearization](https://mlsanity.com/paper/1908.06926/) (2019)
- [A Sequence-to-Set Network for Nested Named Entity Recognition](https://mlsanity.com/paper/2105.08901/) (2021)
- [Nested Named Entity Recognition via Second-best Sequence Learning and Decoding](https://mlsanity.com/paper/1909.02250/) (2019)
- [Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks](https://mlsanity.com/paper/1906.03783/) (2019)
- [A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition](https://mlsanity.com/paper/2106.14373/) (2021)
- [Neural Segmental Hypergraphs for Overlapping Mention Recognition](https://mlsanity.com/paper/1810.01817/) (2018)
- [What's Going On in Neural Constituency Parsers? An Analysis](https://mlsanity.com/paper/1804.07853/) (2018)
- [Merge and Label: A novel neural network architecture for nested NER](https://mlsanity.com/paper/1907.00464/) (2019)
- [Improving Constituency Parsing with Span Attention](https://mlsanity.com/paper/2010.07543/) (2020)
- [Labeling Gaps Between Words: Recognizing Overlapping Mentions with Mention Separators](https://mlsanity.com/paper/1810.09073/) (2018)
- [Bipartite Flat-Graph Network for Nested Named Entity Recognition](https://mlsanity.com/paper/2005.00436/) (2020)
- [Improving Neural Parsing by Disentangling Model Combination and Reranking Effects](https://mlsanity.com/paper/1707.03058/) (2017)

## Abstract (arXiv)

As a fundamental natural language processing task and one of core knowledge extraction techniques, named entity recognition (NER) is widely used to extract information from texts for downstream tasks. Nested NER is a branch of NER in which the named entities (NEs) are nested with each other. However, most of the previous studies on nested NER usually apply linear structure to model the nested NEs which are actually accommodated in a hierarchical structure. Thus in order to address this mismatch, this work models the full nested NEs in a sentence as a holistic structure, then we propose a holistic structure parsing algorithm to disclose the entire NEs once for all. Besides, there is no research on applying corpus-level information to NER currently. To make up for the loss of this information, we introduce Point-wise Mutual Information (PMI) and other frequency features from corpus-aware statistics for even better performance by holistic modeling from sentence-level to corpus-level. Experiments show that our model yields promising results on widely-used benchmarks which approach or even achieve state-of-the-art. Further empirical studies show that our proposed corpus-aware features can substantially improve NER domain adaptation, which demonstrates the surprising advantage of our proposed corpus-level holistic structure modeling.