scholarly journals Ensemble of deep masked language models for effective named entity recognition in multi-domain corpora

2021 ◽  
Author(s):  
Nona Naderi ◽  
Julien Knafou ◽  
Jenny Copara ◽  
Patrick Ruch ◽  
Douglas Teodoro
Keyword(s):  
Named Entity Recognition ◽  
Entity Recognition ◽  
Language Models ◽  
Free Text ◽  
Percentage Point Increase ◽  
Named Entity ◽  
Secondary Use ◽  
Point Increase ◽  
Wet Lab ◽  
Multiple Domains

AbstractThe health and life science domains are well known for their wealth of entities. These entities are presented as free text in large corpora, such as biomedical scientific and electronic health records. To enable the secondary use of these corpora and unlock their value, named entity recognition (NER) methods are proposed. Inspired by the success of deep masked language models, we present an ensemble approach for NER using these models. Results show statistically significant improvement of the ensemble models over baselines based on individual models in multiple domains - chemical, clinical and wet lab - and languages - English and French. The ensemble model achieves an overall performance of 79.2% macro F1-score, a 4.6 percentage point increase upon the baseline in multiple domains and languages. These results suggests that ensembles are a more effective strategy for tackling NER. We further perform a detailed analysis of their performance based on a set of entity properties.

scholarly journals Ensemble of Deep Masked Language Models for Effective Named Entity Recognition in Health and Life Science Corpora

2021 ◽  
Vol 6 ◽  
Author(s):  
Nona Naderi ◽  
Julien Knafou ◽  
Jenny Copara ◽  
Patrick Ruch ◽  
Douglas Teodoro
Keyword(s):  
Life Science ◽  
Named Entity Recognition ◽  
Majority Voting ◽  
Entity Recognition ◽  
Language Models ◽  
Free Text ◽  
Specific Domain ◽  
Named Entities ◽  
Named Entity ◽  
Text Corpora

The health and life science domains are well known for their wealth of named entities found in large free text corpora, such as scientific literature and electronic health records. To unlock the value of such corpora, named entity recognition (NER) methods are proposed. Inspired by the success of transformer-based pretrained models for NER, we assess how individual and ensemble of deep masked language models perform across corpora of different health and life science domains—biology, chemistry, and medicine—available in different languages—English and French. Individual deep masked language models, pretrained on external corpora, are fined-tuned on task-specific domain and language corpora and ensembled using classical majority voting strategies. Experiments show statistically significant improvement of the ensemble models over an individual BERT-based baseline model, with an overall best performance of 77% macro F1-score. We further perform a detailed analysis of the ensemble results and show how their effectiveness changes according to entity properties, such as length, corpus frequency, and annotation consistency. The results suggest that the ensembles of deep masked language models are an effective strategy for tackling NER across corpora from the health and life science domains.

Developing a RadLex-based Named Entity Recognition Tool for Mining Textual Radiology Reports (Preprint)

2020 ◽  
Author(s):  
Shintaro Tsuji ◽  
Andrew Wen ◽  
Naoki Takahashi ◽  
Hongjian Zhang ◽  
Katsuhiko Ogasawara ◽  
...  
Keyword(s):  
Named Entity Recognition ◽  
Noun Phrases ◽  
General Purpose ◽  
Entity Recognition ◽  
Free Text ◽  
Clinical Text ◽  
Named Entity ◽  
Radiology Reports ◽  
Two Measures ◽  
F Measure

BACKGROUND Named entity recognition (NER) plays an important role in extracting the features of descriptions for mining free-text radiology reports. However, the performance of existing NER tools is limited because the number of entities depends on its dictionary lookup. Especially, the recognition of compound terms is very complicated because there are a variety of patterns. OBJECTIVE The objective of the study is to develop and evaluate a NER tool concerned with compound terms using the RadLex for mining free-text radiology reports. METHODS We leveraged the clinical Text Analysis and Knowledge Extraction System (cTAKES) to develop customized pipelines using both RadLex and SentiWordNet (a general-purpose dictionary, GPD). We manually annotated 400 of radiology reports for compound terms (Cts) in noun phrases and used them as the gold standard for the performance evaluation (precision, recall, and F-measure). Additionally, we also created a compound-term-enhanced dictionary (CtED) by analyzing false negatives (FNs) and false positives (FPs), and applied it for another 100 radiology reports for validation. We also evaluated the stem terms of compound terms, through defining two measures: an occurrence ratio (OR) and a matching ratio (MR). RESULTS The F-measure of the cTAKES+RadLex+GPD was 32.2% (Precision 92.1%, Recall 19.6%) and that of combined the CtED was 67.1% (Precision 98.1%, Recall 51.0%). The OR indicated that stem terms of “effusion”, "node", "tube", and "disease" were used frequently, but it still lacks capturing Cts. The MR showed that 71.9% of stem terms matched with that of ontologies and RadLex improved about 22% of the MR from the cTAKES default dictionary. The OR and MR revealed that the characteristics of stem terms would have the potential to help generate synonymous phrases using ontologies. CONCLUSIONS We developed a RadLex-based customized pipeline for parsing radiology reports and demonstrated that CtED and stem term analysis has the potential to improve dictionary-based NER performance toward expanding vocabularies.

Towards corpus and model: Hierarchical structured-attention-based features for Indonesian named entity recognition

2021 ◽  
pp. 1-12
Author(s):  
Yingwen Fu ◽  
Nankai Lin ◽  
Xiaotian Lin ◽  
Shengyi Jiang
Keyword(s):  
Language Processing ◽  
State Of The Art ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Language Models ◽  
Neural Models ◽  
Performance Models ◽  
Named Entity ◽  
High Resource ◽  
Benchmark Datasets

Named entity recognition (NER) is fundamental to natural language processing (NLP). Most state-of-the-art researches on NER are based on pre-trained language models (PLMs) or classic neural models. However, these researches are mainly oriented to high-resource languages such as English. While for Indonesian, related resources (both in dataset and technology) are not yet well-developed. Besides, affix is an important word composition for Indonesian language, indicating the essentiality of character and token features for token-wise Indonesian NLP tasks. However, features extracted by currently top-performance models are insufficient. Aiming at Indonesian NER task, in this paper, we build an Indonesian NER dataset (IDNER) comprising over 50 thousand sentences (over 670 thousand tokens) to alleviate the shortage of labeled resources in Indonesian. Furthermore, we construct a hierarchical structured-attention-based model (HSA) for Indonesian NER to extract sequence features from different perspectives. Specifically, we use an enhanced convolutional structure as well as an enhanced attention structure to extract deeper features from characters and tokens. Experimental results show that HSA establishes competitive performance on IDNER and three benchmark datasets.

scholarly journals Overview of CCKS 2020 Task 3: Named Entity Recognition and Event Extraction in Chinese Electronic Medical Records

2021 ◽  
pp. 1-13
Author(s):  
Xia Li ◽  
Qinghua Wen ◽  
Zengtao Jiao ◽  
Jiangtao Zhang
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Named Entity Recognition ◽  
Event Extraction ◽  
Entity Recognition ◽  
Language Models ◽  
Data Sets ◽  
External Resources ◽  
Named Entity ◽  
Evaluation Task

Abstract The China Conference on Knowledge Graph and Semantic Computing (CCKS) 2020 Evaluation Task 3 presented clinical named entity recognition and event extraction for the Chinese electronic medical records. Two annotated data sets and some other additional resources for these two subtasks were provided for participators. This evaluation competition attracted 354 teams and 46 of them successfully submitted the valid results. The pre-trained language models are widely applied in this evaluation task. Data argumentation and external resources are also helpful.

scholarly journals Information Extraction from Electronic Medical Records Using Multitask Recurrent Neural Network with Contextual Word Embedding

2019 ◽  
Vol 9 (18) ◽  
pp. 3658 ◽  
Author(s):  
Jianliang Yang ◽  
Yuenan Liu ◽  
Minghui Qian ◽  
Chenghua Guan ◽  
Xiangfei Yuan
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Large Scale ◽  
Short Term Memory ◽  
Conditional Random Field ◽  
Named Entity Recognition ◽  
Recognition Task ◽  
Entity Recognition ◽  
Language Models ◽  
Named Entity

Clinical named entity recognition is an essential task for humans to analyze large-scale electronic medical records efficiently. Traditional rule-based solutions need considerable human effort to build rules and dictionaries; machine learning-based solutions need laborious feature engineering. For the moment, deep learning solutions like Long Short-term Memory with Conditional Random Field (LSTM–CRF) achieved considerable performance in many datasets. In this paper, we developed a multitask attention-based bidirectional LSTM–CRF (Att-biLSTM–CRF) model with pretrained Embeddings from Language Models (ELMo) in order to achieve better performance. In the multitask system, an additional task named entity discovery was designed to enhance the model’s perception of unknown entities. Experiments were conducted on the 2010 Informatics for Integrating Biology & the Bedside/Veterans Affairs (I2B2/VA) dataset. Experimental results show that our model outperforms the state-of-the-art solution both on the single model and ensemble model. Our work proposes an approach to improve the recall in the clinical named entity recognition task based on the multitask mechanism.

scholarly journals MenuNER: Domain-Adapted BERT Based NER Approach for a Domain with Limited Dataset and Its Application to Food Menu Domain

2021 ◽  
Vol 11 (13) ◽  
pp. 6007
Author(s):  
Muzamil Hussain Syed ◽  
Sun-Tae Chung
Keyword(s):  
Domain Adaptation ◽  
Language Model ◽  
Named Entity Recognition ◽  
Word Embedding ◽  
Fine Tuning ◽  
Entity Recognition ◽  
Language Models ◽  
Feature Vectors ◽  
Named Entity ◽  
Domain Specific

Entity-based information extraction is one of the main applications of Natural Language Processing (NLP). Recently, deep transfer-learning utilizing contextualized word embedding from pre-trained language models has shown remarkable results for many NLP tasks, including Named-entity recognition (NER). BERT (Bidirectional Encoder Representations from Transformers) is gaining prominent attention among various contextualized word embedding models as a state-of-the-art pre-trained language model. It is quite expensive to train a BERT model from scratch for a new application domain since it needs a huge dataset and enormous computing time. In this paper, we focus on menu entity extraction from online user reviews for the restaurant and propose a simple but effective approach for NER task on a new domain where a large dataset is rarely available or difficult to prepare, such as food menu domain, based on domain adaptation technique for word embedding and fine-tuning the popular NER task network model ‘Bi-LSTM+CRF’ with extended feature vectors. The proposed NER approach (named as ‘MenuNER’) consists of two step-processes: (1) Domain adaptation for target domain; further pre-training of the off-the-shelf BERT language model (BERT-base) in semi-supervised fashion on a domain-specific dataset, and (2) Supervised fine-tuning the popular Bi-LSTM+CRF network for downstream task with extended feature vectors obtained by concatenating word embedding from the domain-adapted pre-trained BERT model from the first step, character embedding and POS tag feature information. Experimental results on handcrafted food menu corpus from customers’ review dataset show that our proposed approach for domain-specific NER task, that is: food menu named-entity recognition, performs significantly better than the one based on the baseline off-the-shelf BERT-base model. The proposed approach achieves 92.5% F1 score on the YELP dataset for the MenuNER task.

Sign in / Sign up

Export Citation Format

Share Document