# Nested Named Entity Recognition with Partially-Observed TreeCRFs

arXiv: https://arxiv.org/abs/2012.08478 · HTML: https://mlsanity.com/paper/2012.08478/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2020.

## Built on by (most cited first, 23 of 23)

- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [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)
- [Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments](https://mlsanity.com/paper/2110.06865/) (2021)
- [Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing](https://mlsanity.com/paper/2203.04665/) (2022)
- [Context-NER : Contextual Phrase Generation at Scale](https://mlsanity.com/paper/2109.08079/) (2021)
- [BIOS: An Algorithmically Generated Biomedical Knowledge Graph](https://mlsanity.com/paper/2203.09975/) (2022)
- [Jointly Learning Span Extraction and Sequence Labeling for Information Extraction from Business Documents](https://mlsanity.com/paper/2205.13434/) (2022)
- [Multi-task Transformer with Relation-attention and Type-attention for Named Entity Recognition](https://mlsanity.com/paper/2303.10870/) (2023)
- [A New Entity Extraction Method Based on Machine Reading Comprehension](https://mlsanity.com/paper/2108.06444/) (2021)
- [A dynamic programming algorithm for span-based nested named-entity recognition in O(n^2)](https://mlsanity.com/paper/2210.04738/) (2022)
- [Few-Shot Nested Named Entity Recognition](https://mlsanity.com/paper/2212.00953/) (2022)
- [To be Continuous, or to be Discrete, Those are Bits of Questions](https://mlsanity.com/paper/2406.07812/) (2024)
- [DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit](https://mlsanity.com/paper/2310.09501/) (2023)
- [Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing](https://mlsanity.com/paper/2407.04801/) (2024)
- [Local Hypergraph-based Nested Named Entity Recognition as Query-based Sequence Labeling](https://mlsanity.com/paper/2204.11467/) (2022)
- [Improving Text Matching in E-Commerce Search with A Rationalizable, Intervenable and Fast Entity-Based Relevance Model](https://mlsanity.com/paper/2307.00370/) (2023)
- [Composited-Nested-Learning with Data Augmentation for Nested Named Entity Recognition](https://mlsanity.com/paper/2406.12779/) (2024)
- [Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations](https://mlsanity.com/paper/2501.19093/) (2025)
- [Nested Named Entity Recognition as Single-Pass Sequence Labeling](https://mlsanity.com/paper/2505.16855/) (2025)
- [Lexicalized Constituency Parsing for Middle Dutch: Low-resource Training and Cross-Domain Generalization](https://mlsanity.com/paper/2601.07008/) (2026)
- [Nested Named Entity Recognition in Plasma Physics Research Articles](https://mlsanity.com/paper/2602.11163/) (2026)
- [Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey](https://mlsanity.com/paper/2607.09666/) (2026)

## Abstract (arXiv)

Named entity recognition (NER) is a well-studied task in natural language processing. However, the widely-used sequence labeling framework is difficult to detect entities with nested structures. In this work, we view nested NER as constituency parsing with partially-observed trees and model it with partially-observed TreeCRFs. Specifically, we view all labeled entity spans as observed nodes in a constituency tree, and other spans as latent nodes. With the TreeCRF we achieve a uniform way to jointly model the observed and the latent nodes. To compute the probability of partial trees with partial marginalization, we propose a variant of the Inside algorithm, the textscMasked Inside algorithm, that supports different inference operations for different nodes (evaluation for the observed, marginalization for the latent, and rejection for nodes incompatible with the observed) with efficient parallelized implementation, thus significantly speeding up training and inference. Experiments show that our approach achieves the state-of-the-art (SOTA) F1 scores on the ACE2004, ACE2005 dataset, and shows comparable performance to SOTA models on the GENIA dataset. Our approach is implemented at: urlhttps://github.com/FranxYao/Partially-Observed-TreeCRFs.