• Corpus ID: 246240785

BTPK-based learning: An Interpretable Method for Named Entity Recognition

@article{Chen2022BTPKbasedLA,
  title={BTPK-based learning: An Interpretable Method for Named Entity Recognition},
  author={Yulin Chen and Zelai Yao and Haixiao Chi and Dov M. Gabbay and Bo Yuan and Bruno Bentzen and Beishui Liao},
  journal={ArXiv},
  year={2022},
  volume={abs/2201.09523}
}
Named entity recognition (NER) is an essential task in natural language processing, but the internal mechanism of most NER models is a black box for users. In some high-stake decision-making areas, improving the interpretability of an NER method is crucial but challenging. In this paper, based on the existing Deterministic Talmudic Public announcement logic (TPK) model, we propose a novel binary tree model (called BTPK) and apply it to two widely used Bi-RNNs to obtain BTPK-based interpretable… 

References

SHOWING 1-10 OF 16 REFERENCES
TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
TLDR
The proposed model, Trigger Matching Network, jointly learns trigger representations and soft matching module with self-attention such that can generalize to unseen sentences easily for tagging, and is significantly more cost-effective than the traditional neural NER frameworks.
Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve
TLDR
It is found that context does influence predictions, but the main factor driving high performance is learning the named tokens themselves, and designing models that explicitly operate over representations of local inputs and context, respectively, may in some cases improve performance.
A Survey on Deep Learning for Named Entity Recognition
TLDR
A comprehensive review on existing deep learning techniques for NER, including tagged NER corpora and off-the-shelf NER tools, and systematically categorizes existing works based on a taxonomy along three axes.
Interpretable Multi-dataset Evaluation for Named Entity Recognition
TLDR
The proposed evaluation method enables us to interpret the differences in models and datasets, as well as the interplay between them, identifying the strengths and weaknesses of current systems.
WCP-RNN: a novel RNN-based approach for Bio-NER in Chinese EMRs
TLDR
This work proposes an RNN-based approach, WCP-RNN, that combines word embeddings and character embedDings to capture orthographic and lexicosemantic features and outperforms the baseline method.
Application of named entity recognition on tweets during earthquake disaster: a deep learning-based approach
TLDR
Recurrent neural network (RNN)-based approaches considering diversity of activation functions and optimization functions with NER tools are utilized to extract named entities such as organization, person, and location from the tweets and show good results in finding named entities.
Learning With Interpretable Structure From Gated RNN
TLDR
Finite-state automaton (FSA) that processes sequential data have a more interpretable inner mechanism according to the definition of interpretability and can be learned from RNNs as the interpretable structure, and FSA is more trustable than the RNN from which it learned.
Nested Named Entity Recognition Revisited
TLDR
A novel recurrent neural network-based approach to simultaneously handle nested named entity recognition and nested entity mention detection that significantly outperforms existing state-of-the-art methods, which are feature-based.
Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
TLDR
A principled end-to-end framework named deep decipher (D2) for SSL is proposed, it is proved that pseudo-labels are related to network predictions by an exponential link function, which gives a theoretical support for using predictions as pseudo-Labels and it is demonstrated that updating pseudo- Labels by network predictions will make them uncertain.
Named Entity Recognition With Parallel Recurrent Neural Networks
TLDR
A new architecture for named entity recognition employs multiple independent bidirectional LSTM units across the same input and promotes diversity among them by employing an inter-model regularization term and finds a significant reduction in the total number of parameters.
...
...