Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition

@inproceedings{Yuan2021FusingHF,
  title={Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition},
  author={Zheng Yuan and Chuanqi Tan and Songfang Huang and Fei Huang},
  booktitle={Findings},
  year={2021}
}
Nested entities are observed in many domains due to their compositionality, which cannot be easily recognized by the widely-used sequence labeling framework.A natural solution is to treat the task as a span classification problem.To learn better span representation and increase classification performance, it is crucial to effectively integrate heterogeneous factors including inside tokens, boundaries, labels, and related spans which could be contributing to nested entities recognition.To fuse… 
[PDF] Semantic Reader
18 Citations
Highly Influential Citations
5
Background Citations
5
Methods Citations
9

18 Citations

A Marker-based Neural Network System for Extracting Social Determinants of Health

A novel marker-based NER model is developed that outperformed the state-of-the-art span-based models at handling overlapping entities based on the overall Micro-F1 score performance and can improve the understanding and tracking of SDoHs in clinical settings.

DiffusionNER: Boundary Diffusion for Named Entity Recognition

The proposed boundary-denoising diffusion process allows progressive refinement and dynamic sampling of entities, empowering DiffusionNER with efficient and flexible entity generation capability.

GPT-NER: Named Entity Recognition via Large Language Models

GPT-NER exhibits a greater ability in the low-resource and few-shot setups, when the amount of training data is extremely scarce, and performs significantly better than supervised models, which demonstrates the capabilities of GPT-ner in real-world NER applications where the number of labeled examples is limited.

Nested Named Entity Recognition as Corpus Aware Holistic Structure Parsing

This work models the full nested NEs in a sentence as a holistic structure, then introduces 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.

An Embarrassingly Easy but Strong Baseline for Nested Named Entity Recognition

This paper proposes using Convolutional Neural Network (CNN) to model these spatial relations in the score matrix and shows that the model surpasses several recently proposed methods with the same pre-trained encoders.

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective

This work proposes a new paradigm for universal information extraction that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment analysis, and develops a traffine attention mechanism to integrate heterogeneous factors including tasks, labels and inside tokens.

Gaussian Prior Reinforcement Learning for Nested Named Entity Recognition

  • Yawen YangXuming Hu Philip S. Yu
  • Computer Science
    ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2023
A novel seq2seq model named GPRL is proposed, which formulates the nested NER task as an entity triplet sequence generation process and designs a Gaussian prior to represent the boundary distance distribution between nested entities and adjust the output probability distribution of nested boundary tokens.

Planarized sentence representation for nested named entity recognition

Full-span named entity recognition with boundary regression

A Controlled Attention for Nested Named Entity Recognition

The controlled attention mechanism for recognizing named entities is proposed, where task-related cues are implanted into each sentence to indicate boundaries of possible named entities and achieves the state-of-the-art performance in all evaluation datasets.

46 References

Pyramid: A Layered Model for Nested Named Entity Recognition

This paper presents Pyramid, a novel layered model for Nested Named Entity Recognition (nested NER) that achieves state-of-the-art F1 scores in nested NER on ACE-2004, ACE-2005, GENIA, and NNE, and a preliminary experiment confirms the effectiveness of the method in overlapping NER.

Named Entity Recognition as Dependency Parsing

Ideas from graph-based dependency parsing are used to provide the model a global view on the input via a biaffine model and show that the model works well for both nested and flat NER, through evaluation on 8 corpora and achieving SoTA performance on all of them.

A general framework for information extraction using dynamic span graphs

This framework significantly outperforms state-of-the-art on multiple information extraction tasks across multiple datasets reflecting different domains and is good at detecting nested span entities, with significant F1 score improvement on the ACE dataset.

A Sequence-to-Set Network for Nested Named Entity Recognition

A novel sequence-to-set neural network for nested NER with fixed set of learnable vectors to learn the patterns of the valuable spans and is more suitable for such unordered recognition task as it is insensitive to the label order.

Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition

This work proposes a two-stage entity identifier that effectively utilizes the boundary information of entities and partially matched spans during training and outperforms previous state-of-the-art models.

Multi-grained Named Entity Recognition

A novel framework for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested, MGNER detects and recognizes entities on multiple granularities and outperforms current state-of-the-art baselines.

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.

Long Short-Term Memory

A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.

Nested Named Entity Recognition with Partially-Observed TreeCRFs

To compute the probability of partial trees with partial marginalization, a variant of the Inside algorithm, the Masked Inside algorithm is proposed 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.

Boundary Enhanced Neural Span Classification for Nested Named Entity Recognition

This work proposes a boundary enhanced neural span classification model that has the ability to generate high-quality candidate spans and greatly reduces the time complexity during inference, and incorporates an additional boundary detection task to predict those words that are boundaries of entities.