Incorporating Dictionaries into Deep Neural Networks for the Chinese Clinical Named Entity Recognition

Wang, Qi; Xia, Yuhang; Zhou, Yangming; Ruan, Tong; Gao, Daqi; He, Ping

doi:10.48550/arxiv.1804.05017

Cited by 6 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from English language, there are many studies on NER on other languages or on cross-lingual setting. For example, Wu et al [116] and Wang et al [132] investigated NER in Chinese clinical text using deep neural networks. Zhang and Yang [133] proposed a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon.…”

Section: Summary Of Dl-based Nermentioning

confidence: 99%

A Survey on Deep Learning for Named Entity Recognition

Sun

Han³

et al. 2022

IEEE Trans. Knowl. Data Eng.

965

397

View full text Add to dashboard Cite

Named entity recognition (NER) is the task to identify text spans that mention named entities, and to classify them into predefined categories such as person, location, organization etc. NER serves as the basis for a variety of natural language applications such as question answering, text summarization, and machine translation. Although early NER systems are successful in producing decent recognition accuracy, they often require much human effort in carefully designing rules or features. In recent years, deep learning, empowered by continuous real-valued vector representations and semantic composition through nonlinear processing, has been employed in NER systems, yielding stat-of-the-art performance. In this paper, we provide a comprehensive review on existing deep learning techniques for NER. We first introduce NER resources, including tagged NER corpora and off-the-shelf NER tools. Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder. Next, we survey the most representative methods for recent applied techniques of deep learning in new NER problem settings and applications. Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.

show abstract

Section: Summary Of Dl-based Nermentioning

confidence: 99%

A Survey on Deep Learning for Named Entity Recognition

Sun

Han³

et al. 2022

IEEE Trans. Knowl. Data Eng.

965

397

View full text Add to dashboard Cite

show abstract

“…Note that the dictionary features also take the position of a character in an entity into account via the BIEOS tag scheme. More details can be seen in our previous work [12].…”

Section: A Embedding Layermentioning

confidence: 99%

“…Traditionally, rule-based approaches [4], [5], dictionarybased approaches [6], [7] and machine learning approaches [8]- [10] are applied to address the CNER tasks. Recently, along with the development of deep learning, some Recurrent Neural Network (RNN) based models, especially for the Bi-LSTM-CRF models [1], [11], [12], have been successfully used and achieved the state-of-the-art results. However, RNN models are dedicated sequence models which maintain a vector of hidden activations that are propagated through time, thus requiring too much time for training.…”

Section: Introductionmentioning

confidence: 99%

Fast and Accurate Recognition of Chinese Clinical Named Entities with Residual Dilated Convolutions

Qiu

Wang

Zhou

et al. 2018

2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

Self Cite

View full text Add to dashboard Cite

Clinical Named Entity Recognition (CNER) aims to identify and classify clinical terms such as diseases, symptoms, treatments, exams, and body parts in electronic health records, which is a fundamental and crucial task for clinical and translation research. In recent years, deep learning methods have achieved significant success in CNER tasks. However, these methods depend greatly on Recurrent Neural Networks (RNNs), which maintain a vector of hidden activations that are propagated through time, thus causing too much time to train models. In this paper, we propose a Residual Dilated Convolutional Neural Network with Conditional Random Field (RD-CNN-CRF) to solve it. Specifically, Chinese characters and dictionary features are first projected into dense vector representations, then they are fed into the residual dilated convolutional neural network to capture contextual features. Finally, a conditional random field is employed to capture dependencies between neighboring tags. Computational results on the CCKS-2017 Task 2 benchmark dataset show that our proposed RD-CNN-CRF method competes favorably with state-of-the-art RNN-based methods both in terms of computational performance and training time.

show abstract

“…Many studies have focused on the clinical named entity recognition (CNER) tasks and most of them formulate the task as a sequence labeling problem, employing various machine learning algorithms to address it [32], [33]. In our previous work [34], we also proposed a CNER model which combines data-driven deep learning approaches and knowledge-driven dictionary approaches. As to this task, due to the limited entities, here we simply utilize string matching and regular matching methods for entity recognition.…”

Section: B Clinical Named Entity Recognitionmentioning

confidence: 99%

Automatic Severity Classification of Coronary Artery Disease via Recurrent Capsule Network

Wang

Qiu

Zhou

et al. 2018

2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

Self Cite

View full text Add to dashboard Cite

Coronary artery disease (CAD) is one of the leading causes of cardiovascular disease deaths. CAD condition progresses rapidly, if not diagnosed and treated at an early stage may eventually lead to an irreversible state of the heart muscle death. Invasive coronary arteriography is the gold standard technique for CAD diagnosis. Coronary arteriography texts describe which part has stenosis and how much stenosis is in details. It is crucial to conduct the severity classification of CAD. In this paper, we employ a recurrent capsule network (RCN) to extract semantic relations between clinical named entities in Chinese coronary arteriography texts, through which we can automatically find out the maximal stenosis for each lumen to inference how severe CAD is according to the improved method of Gensini. Experimental results on the corpus collected from Shanghai Shuguang Hospital show that our proposed method achieves an accuracy of 97.0% in the severity classification of CAD.

show abstract

Incorporating Dictionaries into Deep Neural Networks for the Chinese Clinical Named Entity Recognition

Cited by 6 publications

References 20 publications

A Survey on Deep Learning for Named Entity Recognition

A Survey on Deep Learning for Named Entity Recognition

Fast and Accurate Recognition of Chinese Clinical Named Entities with Residual Dilated Convolutions

Automatic Severity Classification of Coronary Artery Disease via Recurrent Capsule Network

Contact Info

Product

Resources

About