# Discontinuous Named Entity Recognition as Maximal Clique Discovery

arXiv: https://arxiv.org/abs/2106.00218 · HTML: https://mlsanity.com/paper/2106.00218/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 1 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [Named Entity Recognition with Bidirectional LSTM-CNNs](https://mlsanity.com/paper/1511.08308/) (2015)
- [Bridging the Gap between Training and Inference for Neural Machine Translation](https://mlsanity.com/paper/1906.02448/) (2019)
- [Chinese NER Using Lattice LSTM](https://mlsanity.com/paper/1805.02023/) (2018)
- [TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking](https://mlsanity.com/paper/2010.13415/) (2020)
- [Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy](https://mlsanity.com/paper/1909.04273/) (2019)
- [An Effective Transition-based Model for Discontinuous NER](https://mlsanity.com/paper/2004.13454/) (2020)
- [Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media](https://mlsanity.com/paper/2010.01150/) (2020)
- [Combining Spans into Entities: A Neural Two-Stage Approach for Recognizing Discontiguous Entities](https://mlsanity.com/paper/1909.00930/) (2019)
- [Learning to Recognize Discontiguous Entities](https://mlsanity.com/paper/1810.08579/) (2018)

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

- [Unified Named Entity Recognition as Word-Word Relation Classification](https://mlsanity.com/paper/2112.10070/) (2021)
- [A sequence-to-sequence approach for document-level relation extraction](https://mlsanity.com/paper/2204.01098/) (2022)
- [Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction](https://mlsanity.com/paper/2310.11016/) (2023)
- [OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction](https://mlsanity.com/paper/2209.02693/) (2022)
- [CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation](https://mlsanity.com/paper/2210.07022/) (2022)
- [Mirror: A Universal Framework for Various Information Extraction Tasks](https://mlsanity.com/paper/2311.05419/) (2023)
- [BIOS: An Algorithmically Generated Biomedical Knowledge Graph](https://mlsanity.com/paper/2203.09975/) (2022)
- [TOE: A Grid-Tagging Discontinuous NER Model Enhanced by Embedding Tag/Word Relations and More Fine-Grained Tags](https://mlsanity.com/paper/2211.00684/) (2022)
- [A Survey on Arabic Named Entity Recognition: Past, Recent Advances, and Future Trends](https://mlsanity.com/paper/2302.03512/) (2023)
- [Multi-task Transformer with Relation-attention and Type-attention for Named Entity Recognition](https://mlsanity.com/paper/2303.10870/) (2023)
- [A fast and sound tagging method for discontinuous named-entity recognition](https://mlsanity.com/paper/2409.16243/) (2024)
- [UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents](https://mlsanity.com/paper/2408.01038/) (2024)
- [Towards Generalized Open Information Extraction](https://mlsanity.com/paper/2211.15987/) (2022)
- [TriG-NER: Triplet-Grid Framework for Discontinuous Named Entity Recognition](https://mlsanity.com/paper/2411.01839/) (2024)
- [On Fusing ChatGPT and Ensemble Learning in Discon-tinuous Named Entity Recognition in Health Corpora](https://mlsanity.com/paper/2412.16976/) (2024)
- [GapDNER: A Gap-Aware Grid Tagging Model for Discontinuous Named Entity Recognition](https://mlsanity.com/paper/2510.10927/) (2025)
- [SEDA: A Self-Adapted Entity-Centric Data Augmentation for Boosting Gird-based Discontinuous NER Models](https://mlsanity.com/paper/2511.20143/) (2025)

## Abstract (arXiv)

Named entity recognition (NER) remains challenging when entity mentions can be discontinuous. Existing methods break the recognition process into several sequential steps. In training, they predict conditioned on the golden intermediate results, while at inference relying on the model output of the previous steps, which introduces exposure bias. To solve this problem, we first construct a segment graph for each sentence, in which each node denotes a segment (a continuous entity on its own, or a part of discontinuous entities), and an edge links two nodes that belong to the same entity. The nodes and edges can be generated respectively in one stage with a grid tagging scheme and learned jointly using a novel architecture named Mac. Then discontinuous NER can be reformulated as a non-parametric process of discovering maximal cliques in the graph and concatenating the spans in each clique. Experiments on three benchmarks show that our method outperforms the state-of-the-art (SOTA) results, with up to 3.5 percentage points improvement on F1, and achieves 5x speedup over the SOTA model.