# Cross-domain Named Entity Recognition via Graph Matching

arXiv: https://arxiv.org/abs/2408.00981 · HTML: https://mlsanity.com/paper/2408.00981/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 2 Aug 2024.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Optimal Transport for structured data with application on graphs](https://mlsanity.com/paper/1805.09114/) (2018)
- [Template-Based Named Entity Recognition Using BART](https://mlsanity.com/paper/2106.01760/) (2021)
- [Gromov-Wasserstein Alignment of Word Embedding Spaces](https://mlsanity.com/paper/1809.00013/) (2018)
- [CrossNER: Evaluating Cross-Domain Named Entity Recognition](https://mlsanity.com/paper/2012.04373/) (2020)
- [Graph Optimal Transport for Cross-Domain Alignment](https://mlsanity.com/paper/2006.14744/) (2020)
- [Towards Lifelong Learning of Large Language Models: A Survey](https://mlsanity.com/paper/2406.06391/) (2024)
- [A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks](https://mlsanity.com/paper/1611.01587/) (2016)
- [Few-Shot Named Entity Recognition: A Comprehensive Study](https://mlsanity.com/paper/2012.14978/) (2020)
- [Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling](https://mlsanity.com/paper/2004.11727/) (2020)
- [Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward Transfer](https://mlsanity.com/paper/2401.09181/) (2024)
- [Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks](https://mlsanity.com/paper/1703.06345/) (2017)
- [Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition](https://mlsanity.com/paper/2106.15167/) (2021)
- [Zero-Resource Cross-Domain Named Entity Recognition](https://mlsanity.com/paper/2002.05923/) (2020)
- [Transfer Learning for Named-Entity Recognition with Neural Networks](https://mlsanity.com/paper/1705.06273/) (2017)
- [Neural Adaptation Layers for Cross-domain Named Entity Recognition](https://mlsanity.com/paper/1810.06368/) (2018)
- [Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference](https://mlsanity.com/paper/2306.10790/) (2023)
- [Incremental Sequence Labeling: A Tale of Two Shifts](https://mlsanity.com/paper/2402.10447/) (2024)

## Built on by (most cited first, 5 of 5)

- [Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large Language Model](https://mlsanity.com/paper/2411.00451/) (2024)
- [Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentation](https://mlsanity.com/paper/2603.15475/) (2026)
- [Graph Similarity Computation via Interpretable Neural Node Alignment](https://mlsanity.com/paper/2412.12185/) (2024)
- [Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition](https://mlsanity.com/paper/2606.21890/) (2026)
- [NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning](https://mlsanity.com/paper/2609.02366/) (2026)

## Abstract (arXiv)

Cross-domain NER is a practical yet challenging problem since the data scarcity in the real-world scenario. A common practice is first to learn a NER model in a rich-resource general domain and then adapt the model to specific domains. Due to the mismatch problem between entity types across domains, the wide knowledge in the general domain can not effectively transfer to the target domain NER model. To this end, we model the label relationship as a probability distribution and construct label graphs in both source and target label spaces. To enhance the contextual representation with label structures, we fuse the label graph into the word embedding output by BERT. By representing label relationships as graphs, we formulate cross-domain NER as a graph matching problem. Furthermore, the proposed method has good applicability with pre-training methods and is potentially capable of other cross-domain prediction tasks. Empirical results on four datasets show that our method outperforms a series of transfer learning, multi-task learning, and few-shot learning methods.