E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition
3
Citation
37
Reference
10
Related Paper
Citation Trend
Abstract:
Most named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty, which is critical to the reliability of NER systems in open environments. Evidential deep learning (EDL) has recently been proposed as a promising solution to explicitly model predictive uncertainty for classification tasks. However, directly applying EDL to NER applications faces two challenges, i.e., the problems of sparse entities and OOV/OOD entities in NER tasks. To address these challenges, we propose a trustworthy NER framework named E-NER by introducing two uncertainty-guided loss terms to the conventional EDL, along with a series of uncertainty-guided training strategies. Experiments show that E-NER can be applied to multiple NER paradigms to obtain accurate uncertainty estimation. Furthermore, compared to state-of-the-art baselines, the proposed method achieves a better OOV/OOD detection performance and better generalization ability on OOV entities.Keywords:
Named Entity Recognition
Trustworthiness
It is a simple study that trying to examine the gap between the students' expectation on trustworthiness and their perceived trustworthiness. The study formulated four research questions. The implications and recommendation for future research were also presented.
Trustworthiness
Cite
Citations (0)
The availability of large amounts of computer-readable textual data and hardware that can process the data has shifted the focus of knowledge projects towards deep learning architec- ture. Natural Language Processing, particularly the task of Named Entity Recognition is no exception. The bulk of the learning methods that have produced state-of-the-art results have changed the deep learning model, the training method used, the training data itself or the encoding of the output of the NER system. In this paper, we review significant learning methods that have been employed for NER in the recent past and how they came about from the linear learning methods of the past. We also cover the progress of related tasks that are upstream or downstream to NER eg. sequence tagging, entity linking etc. wherever the processes in question have also improved NER results.
Named Entity Recognition
Sequence labeling
Cite
Citations (0)
Thinking is, by necessity, associated with generalization; thinking is done in generalizations and leads to generalizations of a higher and higher order. The very transition from problem-solving by...
Abstraction
Cite
Citations (0)
The availability of large amounts of computer-readable textual data and hardware that can process the data has shifted the focus of knowledge projects towards deep learning architecture. Natural Language Processing, particularly the task of Named Entity Recognition is no exception. The bulk of the learning methods that have produced state-of-the-art results have changed the deep learning model, the training method used, the training data itself or the encoding of the output of the NER system. In this paper, we review significant learning methods that have been employed for NER in the recent past and how they came about from the linear learning methods of the past. We also cover the progress of related tasks that are upstream or downstream to NER, e.g., sequence tagging, entity linking, etc., wherever the processes in question have also improved NER results.
Named Entity Recognition
Sequence labeling
Cite
Citations (19)
Fine-Grained Named Entity Recognition (FG-NER) is critical for many NLP applications. While classical named entity recognition (NER) has attracted a substantial amount of research, FG-NER is still an open research domain. The current state-of-the-art (SOTA) model for FG-NER relies heavily on manual efforts for building a dictionary and designing hand-crafted features. The end-to-end framework which achieved the SOTA result for NER did not get the competitive result compared to SOTA model for FG-NER. In this paper, we investigate how effective multi-task learning approaches are in an end-to-end framework for FG-NER in different aspects. Our experiments show that using multi-task learning approaches with contextualized word representation can help an end-to-end neural network model achieve SOTA results without using any additional manual effort for creating data and designing features.
Named Entity Recognition
Representation
Entity linking
Cite
Citations (3)
Abstract: Deep fake is a rapidly growing concern in society, and it has become a significant challenge to detect such manipulated media. Deep fake detection involves identifying whether a media file is authentic or generated using deep learning algorithms. In this project, we propose a deep learning-based approach for detecting deep fakes in videos. We use the Deep fake Detection Challenge dataset, which consists of real and Deep fake videos, to train and evaluate our deep learning model. We employ a Convolutional Neural Network (CNN) architecture for our implementation, which has shown great potential in previous studies. We pre-process the dataset using several techniques such as resizing, normalization, and data augmentation to enhance the quality of the input data. Our proposed model achieves high detection accuracy of 97.5% on the Deep fake Detection Challenge dataset, demonstrating the effectiveness of the proposed approach for deep fake detection. Our approach has the potential to be used in real-world scenarios to detect deep fakes, helping to mitigate the risks posed by deep fakes to individuals and society. The proposed methodology can also be extended to detect in other types of media, such as images and audio, providing a comprehensive solution for deep fake detection.
Deep Neural Networks
Normalization
Cite
Citations (2)
Biomedical named entity recognition (BioNER) is one subtask of named entity recognition (NER) research. Although there are a number of named entity recognition systems, they can not obtain good performances extended to biomedical subfield. BioNER becomes a challenging work. We employ a skip-chain conditional random fields (CRFs) model for BioNER. This model completely considers to the long-range dependencies about biomedical information. These distant dependencies are powerful to identify some frequent appearing named entities and to classify them, especially for both classes protein and cell type. When we test the GENIA corpus, our approach obtains significant improvement over other methods, which achieves precision, recall and F-score of 72.8%, 73.6% and 73.2%, respectively.
CRFS
Named Entity Recognition
Named entity
Entity linking
Biomedical text mining
F1 score
Cite
Citations (23)
Named Entity Recognition
Sequence labeling
Entity linking
Cite
Citations (1)
In this paper, we present our Named Entity Recognition (NER) system for German – NERU (Named Entity Rules), which heavily relies on handcrafted rules as well as information gained from a cascade of existing external NER tools. The system combines large gazetteer lists, information obtained by comparison of different automatic translations and POS taggers. With NERU, we were able to achieve a score of 73.26% on the development set provided by the GermEval 2014 Named Entity Recognition Shared Task for German.
Named Entity Recognition
Entity linking
Named entity
Cite
Citations (6)
Abstract Named Entity Recognition (NER) is a key task in Natural Language Processing (NLP). In medical domain, NER is very important phase in all end-to-end systems. In this paper, we investigate the performance of NER for disease (D-NER). TaggerOne was evaluated on 52 cardiovascular-related clinical case reports against hand annotation for diseases. Different training sets have been used to evaluate the performance of TaggerOne as a famous tool for NER in biomedical domain.
Named Entity Recognition
Entity linking
Named entity
Cite
Citations (0)