# Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss

arXiv: https://arxiv.org/abs/2108.07216 · HTML: https://mlsanity.com/paper/2108.07216/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 51 references that are in the map.
- First posted on arXiv 16 Aug 2021.

## Builds on (most cited first, 17 of 17)

- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://mlsanity.com/paper/1603.01354/) (2016)
- [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency](https://mlsanity.com/paper/1809.01812/) (2018)
- [Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning](https://mlsanity.com/paper/1906.01378/) (2019)
- [Cloze-driven Pretraining of Self-attention Networks](https://mlsanity.com/paper/1903.07785/) (2019)
- [Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition](https://mlsanity.com/paper/2012.05426/) (2020)
- [Named Entity Recognition with Partially Annotated Training Data](https://mlsanity.com/paper/1909.09270/) (2019)
- [Exploring Cross-sentence Contexts for Named Entity Recognition with BERT](https://mlsanity.com/paper/2006.01563/) (2020)
- [Generalisation in Named Entity Recognition: A Quantitative Analysis](https://mlsanity.com/paper/1701.02877/) (2017)
- [Active Learning for Coreference Resolution using Discrete Annotation](https://mlsanity.com/paper/2004.13671/) (2020)

## Built on by (most cited first, 7 of 7)

- [On the inconsistency of separable losses for structured prediction](https://mlsanity.com/paper/2301.10810/) (2023)
- [Partial Annotation Learning for Biomedical Entity Recognition](https://mlsanity.com/paper/2305.13120/) (2023)
- [Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels](https://mlsanity.com/paper/2406.16293/) (2024)
- [Few Dimensions are Enough: Fine-tuning BERT with Selected Dimensions Revealed Its Redundant Nature](https://mlsanity.com/paper/2504.04966/) (2025)
- [AdaK-NER: An Adaptive Top-K Approach for Named Entity Recognition with Incomplete Annotations](https://mlsanity.com/paper/2109.05233/) (2021)
- [Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection](https://mlsanity.com/paper/2412.00426/) (2024)
- [Strong Multilingual Privacy Tagging at Encoder Speed](https://mlsanity.com/paper/2609.38630/) (2026)

## Abstract (arXiv)

We study learning named entity recognizers in the presence of missing entity annotations. We approach this setting as tagging with latent variables and propose a novel loss, the Expected Entity Ratio, to learn models in the presence of systematically missing tags. We show that our approach is both theoretically sound and empirically useful. Experimentally, we find that it meets or exceeds performance of strong and state-of-the-art baselines across a variety of languages, annotation scenarios, and amounts of labeled data. In particular, we find that it significantly outperforms the previous state-of-the-art methods from Mayhew et al. (2019) and Li et al. (2021) by +12.7 and +2.3 F1 score in a challenging setting with only 1,000 biased annotations, averaged across 7 datasets. We also show that, when combined with our approach, a novel sparse annotation scheme outperforms exhaustive annotation for modest annotation budgets.