Stacked ensemble combined with fuzzy matching for biomedical named entity recognition of diseases

Biomedical Named Entity Recognition (Bio-NER) is the crucial initial step in the information extraction process and a majorly focused research area in biomedical text mining. In the past years, several models and methodologies have been proposed for the recognition of semantic types related to gene, protein, chemical, drug and other biological relevant named entities. In this paper, we implemented a stacked ensemble approach combined with fuzzy matching for biomedical named entity recognition of disease names. The underlying concept of stacked generalization is to combine the outputs of base-level classifiers using a second-level meta-classifier in an ensemble. We used Conditional Random Field (CRF) as the underlying classification method that makes use of a diverse set of features, mostly based on domain specific, and are orthographic and morphologically relevant. In addition, we used fuzzy string matching to tag rare disease names from our in-house disease dictionary. For fuzzy matching, we incorporated two best fuzzy search algorithms Rabin Karp and Tuned Boyer Moore. Our proposed approach shows promised result of 94.66%, 89.12%, 84.10%, and 76.71% of F-measure while on evaluating training and testing set of both NCBI disease and BioCreative V CDR Corpora.     

Recognizing names in biomedical texts using mutual information independence model and SVM plus sigmoid

In this paper, we present a biomedical name recognition system, called PowerBioNE. In order to deal with the special phenomena in the biomedical domain, various evidential features are proposed and integrated through a mutual information independence model (MIIM). In addition, a support vector machine (SVM) plus sigmoid is proposed to resolve the data sparseness problem in the MIIM. In this way, the data sparseness problem in MIIM-based biomedical name recognition can be resolved effectively and a biomedical name recognition system with better performance and better portability can be achieved. Finally, we present two post-processing modules to deal with the nested entity name and abbreviation phenomena in the biomedical domain to further improve the performance. Evaluation shows that our system achieves F-measures of 69.1 and 71.2 on the 23 classes of GENIA V1.1 and V3.0, respectively. In particular, our system achieves an F-measure of 77.8 on the "protein" class of GENIA V3.0. It also shows that our system outperforms the best-reported system on GENIA V1.1 and V3.0.     

Character-level neural network for biomedical named entity recognition

Biomedical named entity recognition (BNER), which extracts important named entities such as genes and proteins, is a challenging task in automated systems that mine knowledge in biomedical texts. The previous state-of-the-art systems required large amounts of task-specific knowledge in the form of feature engineering, lexicons and data pre-processing to achieve high performance. In this paper, we introduce a novel neural network architecture that benefits from both word- and character-level representations automatically, by using a combination of bidirectional long short-term memory (LSTM) and conditional random field (CRF) eliminating the need for most feature engineering tasks. We evaluate our system on two datasets: JNLPBA corpus and the BioCreAtIvE II Gene Mention (GM) corpus. We obtained state-of-the-art performance by outperforming the previous systems. To the best of our knowledge, we are the first to investigate the combination of deep neural networks, CRF, word embeddings and character-level representation in recognizing biomedical named entities.     

Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts

Named entity recognition is a crucial component of biomedical natural language processing, enabling information extraction and ultimately reasoning over and knowledge discovery from text. Much progress has been made in the design of rule-based and supervised tools, but they are often genre and task dependent. As such, adapting them to different genres of text or identifying new types of entities requires major effort in re-annotation or rule development. In this paper, we propose an unsupervised approach to extracting named entities from biomedical text. We describe a stepwise solution to tackle the challenges of entity boundary detection and entity type classification without relying on any handcrafted rules, heuristics, or annotated data. A noun phrase chunker followed by a filter based on inverse document frequency extracts candidate entities from free text. Classification of candidate entities into categories of interest is carried out by leveraging principles from distributional semantics. Experiments show that our system, especially the entity classification step, yields competitive results on two popular biomedical datasets of clinical notes and biological literature, and outperforms a baseline dictionary match approach. Detailed error analysis provides a road map for future work.     

电子病历中命名实体的智能识别

电子病历中命名实体的识别对于构建和挖掘大型临床数据库以服务于临床决策具有重要意义,而我国目前对此的研究相对较少。在比较现有的实体识别方法和模型后,采用条件随机场模型(CRF)机器学习的方法,对疾病、临床症状、手术操作3类中文病历中常见的命名实体进行智能识别。首先,通过分析电子病历的数据特征,选择以语言符号、词性、构词特征、词边界、上下文为特征集。然后,基于随机抽取的来自临床医院多个科室的电子病历数据,构建小规模语料库并进行标注。最后,利用条件随机场算法执行工具CRF++进行3次对照实验。通过逐步分析特征集中的多种特征对CRF自动识别的影响,提出在中文病历环境下CRF特征选择和模板设计的一些基本规则。在对照实验中,本方法取得了良好效果,3类实体的最佳F值分别达到了92.67%、93.76%和95.06%。     

Rich features based Conditional Random Fields for biological named entities recognition

Biological named entity recognition is a critical task for automatically mining knowledge from biological literature. In this paper, this task is cast as a sequential labeling problem and Conditional Random Fields model is introduced to solve it. Under the framework of Conditional Random Fields model, rich features including literal, context and semantics are involved. Among these features, shallow syntactic features are first introduced, which effectively improve the model's performance. Experiments show that our method can achieve an F-measure of 71.2% in an open evaluation data, which is better than most of state-of-the-art systems.     

Biomedical named entity recognition using two-phase model based on SVMs

Named entity (NE) recognition has become one of the most fundamental tasks in biomedical knowledge acquisition. In this paper, we present a two-phase named entity recognizer based on SVMs, which consists of a boundary identification phase and a semantic classification phase of named entities. When adapting SVMs to named entity recognition, the multi-class problem and the unbalanced class distribution problem become very serious in terms of training cost and performance. We try to solve these problems by separating the NE recognition task into two subtasks, where we use appropriate SVM classifiers and relevant features for each subtask. In addition, by employing a hierarchical classification method based on ontology, we effectively solve the multi-class problem concerning semantic classification. The experimental results on the GENIA corpus show that the proposed method is effective not only in reducing computational cost but also in improving performance. The F-score (beta=1) for the boundary identification is 74.8 and the F-score for the semantic classification is 66.7.     

Using name-internal and contextual features to classify biological terms

There has been considerable work done recently in recognizing named entities in biomedical text. In this paper, we investigate the named entity classification task, an integral part of the named entity extraction task. We focus on the different sources of information that can be utilized for classification, and note the extent to which they are effective in classification. To classify a name, we consider features that appear within the name as well as nearby phrases. We also develop a new strategy based on the context of occurrence and show that they improve the performance of the classification system. We show how our work relates to previous works on named entity classification in the biological domain as well as to those in generic domains. The experiments were conducted on the GENIA corpus Ver. 3.0 developed at University of Tokyo. We achieve f value of 86 in 10-fold cross validation evaluation on this corpus.     

Identifying non-elliptical entity mentions in a coordinated NP with ellipses

Named entities in the biomedical domain are often written using a Noun Phrase (NP) along with a coordinating conjunction such as ‘and’ and ‘or’. In addition, repeated words among named entity mentions are frequently omitted. It is often difficult to identify named entities. Although various Named Entity Recognition (NER) methods have tried to solve this problem, these methods can only deal with relatively simple elliptical patterns in coordinated NPs. We propose a new NER method for identifying non-elliptical entity mentions with simple or complex ellipses using linguistic rules and an entity mention dictionary.The GENIA and CRAFT corpora were used to evaluate the performance of the proposed system. The GENIA corpus was used to evaluate the performance of the system according to the quality of the dictionary. The GENIA corpus comprises 3434 non-elliptical entity mentions in 1585 coordinated NPs with ellipses. The system achieves 92.11% precision, 95.20% recall, and 93.63% F-score in identification of non-elliptical entity mentions in coordinated NPs. The accuracy of the system in resolving simple and complex ellipses is 94.54% and 91.95%, respectively. The CRAFT corpus was used to evaluate the performance of the system under realistic conditions. The system achieved 78.47% precision, 67.10% recall, and 72.34% F-score in coordinated NPs. The performance evaluations of the system show that it efficiently solves the problem caused by ellipses, and improves NER performance. The algorithm is implemented in PHP and the code can be downloaded from https://code.google.com/p/medtextmining/.     

基于ALBERT与BILSTM的糖尿病命名实体识别

糖尿病命名实体识别技术能够从糖尿病文献中识别出关键信息,为糖尿病的诊断和治疗工作提供帮助。为此,本研究提出一种基于轻量型动态词向量模型（ALBERT）与双向长短记忆神经网络的命名实体识别方法,该方法旨在解决BERT语义单一、词汇量有限的问题。除此之外,还针对动态词向量训练耗时长、资源成本高的缺点进行了改进。本实验在糖尿病数据集上展开,并与现有主流模型进行对比。结果表明,融合ALBERT的实体识别效果均高于现有主流模型,且ALBERT较BERT训练速度有所提升。     

Feature selection techniques for maximum entropy based biomedical named entity recognition

Named entity recognition is an extremely important and fundamental task of biomedical text mining. Biomedical named entities include mentions of proteins, genes, DNA, RNA, etc which often have complex structures, but it is challenging to identify and classify such entities. Machine learning methods like CRF, MEMM and SVM have been widely used for learning to recognize such entities from an annotated corpus. The identification of appropriate feature templates and the selection of the important feature values play a very important role in the success of these methods. In this paper, we provide a study on word clustering and selection based feature reduction approaches for named entity recognition using a maximum entropy classifier. The identification and selection of features are largely done automatically without using domain knowledge. The performance of the system is found to be superior to existing systems which do not use domain knowledge.     

PKDE4J: Entity and relation extraction for public knowledge discovery

Due to an enormous number of scientific publications that cannot be handled manually, there is a rising interest in text-mining techniques for automated information extraction, especially in the biomedical field. Such techniques provide effective means of information search, knowledge discovery, and hypothesis generation. Most previous studies have primarily focused on the design and performance improvement of either named entity recognition or relation extraction. In this paper, we present PKDE4J, a comprehensive text-mining system that integrates dictionary-based entity extraction and rule-based relation extraction in a highly flexible and extensible framework. Starting with the Stanford CoreNLP, we developed the system to cope with multiple types of entities and relations. The system also has fairly good performance in terms of accuracy as well as the ability to configure text-processing components. We demonstrate its competitive performance by evaluating it on many corpora and found that it surpasses existing systems with average F-measures of 85% for entity extraction and 81% for relation extraction.     

A study of active learning methods for named entity recognition in clinical text

ObjectivesNamed entity recognition (NER), a sequential labeling task, is one of the fundamental tasks for building clinical natural language processing (NLP) systems. Machine learning (ML) based approaches can achieve good performance, but they often require large amounts of annotated samples, which are expensive to build due to the requirement of domain experts in annotation. Active learning (AL), a sample selection approach integrated with supervised ML, aims to minimize the annotation cost while maximizing the performance of ML-based models. In this study, our goal was to develop and evaluate both existing and new AL methods for a clinical NER task to identify concepts of medical problems, treatments, and lab tests from the clinical notes.MethodsUsing the annotated NER corpus from the 2010 i2b2/VA NLP challenge that contained 349 clinical documents with 20,423 unique sentences, we simulated AL experiments using a number of existing and novel algorithms in three different categories including uncertainty-based, diversity-based, and baseline sampling strategies. They were compared with the passive learning that uses random sampling. Learning curves that plot performance of the NER model against the estimated annotation cost (based on number of sentences or words in the training set) were generated to evaluate different active learning and the passive learning methods and the area under the learning curve (ALC) score was computed.ResultsBased on the learning curves of F-measure vs. number of sentences, uncertainty sampling algorithms outperformed all other methods in ALC. Most diversity-based methods also performed better than random sampling in ALC. To achieve an F-measure of 0.80, the best method based on uncertainty sampling could save 66% annotations in sentences, as compared to random sampling. For the learning curves of F-measure vs. number of words, uncertainty sampling methods again outperformed all other methods in ALC. To achieve 0.80 in F-measure, in comparison to random sampling, the best uncertainty based method saved 42% annotations in words. But the best diversity based method reduced only 7% annotation effort.ConclusionIn the simulated setting, AL methods, particularly uncertainty-sampling based approaches, seemed to significantly save annotation cost for the clinical NER task. The actual benefit of active learning in clinical NER should be further evaluated in a real-time setting.     

Semi-supervised medical entity recognition: A study on Spanish and Swedish clinical corpora

ObjectiveThe goal of this study is to investigate entity recognition within Electronic Health Records (EHRs) focusing on Spanish and Swedish. Of particular importance is a robust representation of the entities. In our case, we utilized unsupervised methods to generate such representations.MethodsThe significance of this work stands on its experimental layout. The experiments were carried out under the same conditions for both languages. Several classification approaches were explored: maximum probability, CRF, Perceptron and SVM. The classifiers were enhanced by means of ensembles of semantic spaces and ensembles of Brown trees. In order to mitigate sparsity of data, without a significant increase in the dimension of the decision space, we propose the use of clustered approaches of the hierarchical Brown clustering represented by trees and vector quantization for each semantic space.ResultsThe results showed that the semi-supervised approaches significantly improved standard supervised techniques for both languages. Moreover, clustering the semantic spaces contributed to the quality of the entity recognition while keeping the dimension of the feature-space two orders of magnitude lower than when directly using the semantic spaces.ConclusionsThe contributions of this study are: (a) a set of thorough experiments that enable comparisons regarding the influence of different types of features on different classifiers, exploring two languages other than English; and (b) the use of ensembles of clusters of Brown trees and semantic spaces on EHRs to tackle the problem of scarcity of available annotated data.     

Automatic recognition of disorders,findings, pharmaceuticals and body structures from clinical text: An annotation and machine learning study

Automatic recognition of clinical entities in the narrative text of health records is useful for constructing applications for documentation of patient care, as well as for secondary usage in the form of medical knowledge extraction. There are a number of named entity recognition studies on English clinical text, but less work has been carried out on clinical text in other languages.This study was performed on Swedish health records, and focused on four entities that are highly relevant for constructing a patient overview and for medical hypothesis generation, namely the entities: Disorder, Finding, Pharmaceutical Drug and Body Structure. The study had two aims: to explore how well named entity recognition methods previously applied to English clinical text perform on similar texts written in Swedish; and to evaluate whether it is meaningful to divide the more general category Medical Problem, which has been used in a number of previous studies, into the two more granular entities, Disorder and Finding.Clinical notes from a Swedish internal medicine emergency unit were annotated for the four selected entity categories, and the inter-annotator agreement between two pairs of annotators was measured, resulting in an average F-score of 0.79 for Disorder, 0.66 for Finding, 0.90 for Pharmaceutical Drug and 0.80 for Body Structure. A subset of the developed corpus was thereafter used for finding suitable features for training a conditional random fields model. Finally, a new model was trained on this subset, using the best features and settings, and its ability to generalise to held-out data was evaluated. This final model obtained an F-score of 0.81 for Disorder, 0.69 for Finding, 0.88 for Pharmaceutical Drug, 0.85 for Body Structure and 0.78 for the combined category Disorder + Finding.The obtained results, which are in line with or slightly lower than those for similar studies on English clinical text, many of them conducted using a larger training data set, show that the approaches used for English are also suitable for Swedish clinical text. However, a small proportion of the errors made by the model are less likely to occur in English text, showing that results might be improved by further tailoring the system to clinical Swedish. The entity recognition results for the individual entities Disorder and Finding show that it is meaningful to separate the general category Medical Problem into these two more granular entity types, e.g. for knowledge mining of co-morbidity relations and disorder-finding relations.     

Improving the performance of dictionary-based approaches in protein name recognition

Dictionary-based protein name recognition is often a first step in extracting information from biomedical documents because it can provide ID information on recognized terms. However, dictionary-based approaches present two fundamental difficulties: (1) false recognition mainly caused by short names; (2) low recall due to spelling variations. In this paper, we tackle the former problem using machine learning to filter out false positives and present two alternative methods for alleviating the latter problem of spelling variations. The first is achieved by using approximate string searching, and the second by expanding the dictionary with a probabilistic variant generator, which we propose in this paper. Experimental results using the GENIA corpus revealed that filtering using a naive Bayes classifier greatly improved precision with only a slight loss of recall, resulting in 10.8% improvement in F-measure, and dictionary expansion with the variant generator gave further 1.6% improvement and achieved an F-measure of 66.6%.     

Boosting performance of gene mention tagging system by hybrid methods

NER (Named Entity Recognition) in biomedical literature is presently one of the internationally concerned NLP (Natural Language Processing) research questions. In order to get higher performance, a hybrid experimental framework is presented for the gene mention tagging task. Six classifiers are firstly constructed by four toolkits (CRF++, YamCha, Maximum Entropy (ME) and MALLET) with different training methods and features sets, and then combined with three different hybrid methods respectively: simple set operation method, voting method and two layer stacking method. Experiments carried out on the corpus of BioCreative II GM task show that the three hybrid methods get the F-measure of 87.40%, 87.31% and 87.70% separately without any post-processing, which are all higher than those of any single ones. Our best hybrid method (two layer stacking method) achieves an F-measure of 88.42% after post-processing, which outperforms most of the state-of-the-art systems. We also discuss the influence on the performance of the ensemble system by the number, performance and divergence of single classifiers in each hybrid method, and give the corresponding analysis why our hybrid models can improve the performance.     

Use of morphological analysis in protein name recognition

Protein name recognition aims to detect each and every protein names appearing in a PubMed abstract. The task is not simple, as the graphic word boundary (space separator) assumed in conventional preprocessing does not necessarily coincide with the protein name boundary. Such boundary disagreement caused by tokenization ambiguity has usually been ignored in conventional preprocessing of general English. In this paper, we argue that boundary disagreement poses serious limitations in biomedical English text processing, not to mention protein name recognition. Our key idea for dealing with the boundary disagreement is to apply techniques used in Japanese morphological analysis where there are no word boundaries. Having evaluated the proposed method with GENIA corpus 3.02, we obtain F-measure of 69.01 on a strict criterion and 79.32 on a relaxed criterion. The result is comparable to other published work in protein name recognition, without resorting to manually prepared ad hoc feature engineering. Further, compared to the conventional preprocessing, the use of morphological analysis as preprocessing improves the performance of protein name recognition and reduces the execution time.     

BOAT: automatic alignment of biomedical ontologies using term informativeness and candidate selection

The biomedical sciences is one of the few domains where ontologies are widely being developed to facilitate information retrieval and knowledge sharing, but there still remains the problem that applications using different ontologies cannot share knowledge without explicit references between overlapping concepts. Ontology alignment is the task of identifying such equivalence relations between concepts across ontologies. Its application to the biomedical domain should address two open issues: (1) determining the equivalence of concept-pairs which have overlapping terms in their names, and (2) the high run-time required to align large ontologies which are typical in the biomedical domain. To address them, we present a novel approach, named the Biomedical Ontologies Alignment Technique (BOAT), which is state-of-the-art in terms of F-measure, precision and speed. A key feature of BOAT is that it considers the informativeness of each component word in the concept labels, which has significant impact on biomedical ontologies, resulting in a 12.2% increase in F-measure. Another important feature of BOAT is that it selects for comparison only concept pairs that show high likelihoods of equivalence, based on the similarity of their annotations. BOAT's F-measure of 0.88 for the alignment of the mouse and human anatomy ontologies is on par with that of another state-of-the-art matcher, AgreementMaker, while taking a shorter time.     

ZK DrugResist 2.0: A TextMiner to extract semantic relations of drug resistance from PubMed

Extracting useful knowledge from an unstructured textual data is a challenging task for biologists, since biomedical literature is growing exponentially on a daily basis. Building an automated method for such tasks is gaining much attention of researchers. ZK DrugResist is an online tool that automatically extracts mutations and expression changes associated with drug resistance from PubMed. In this study we have extended our tool to include semantic relations extracted from biomedical text covering drug resistance and established a server including both of these features. Our system was tested for three relations, Resistance (R), Intermediate (I) and Susceptible (S) by applying hybrid feature set. From the last few decades the focus has changed to hybrid approaches as it provides better results. In our case this approach combines rule-based methods with machine learning techniques. The results showed 97.67% accuracy with 96% precision, recall and F-measure. The results have outperformed the previously existing relation extraction systems thus can facilitate computational analysis of drug resistance against complex diseases and further can be implemented on other areas of biomedicine.