Concept Extraction Research Articles

Relation Extraction of Medical Concepts Using Categorization and Sentiment Analysis

In healthcare services, information extraction is the key to understand any corpus-based knowledge. The process becomes laborious when the annotation is done manually for the availability of a large number of text corpora. Hence, future automated extraction systems will be essential for groups of experts such as doctors and medical practitioners as well as non-experts such as patients, to ensure enhanced clinical decision-making for improving healthcare systems. Such extraction systems can be developed using medical concepts and concept-related features as the part of a structured corpus. The latter can assist in assigning the category and sentiment to each of the medical concepts and their lexical contexts. These categories and sentiment assignments constitute semantic relations of medical concepts, with their context, represented by sentences of the corpus. This paper presents a new domain-based knowledge lexicon coupled with a machine learning approach to extract semantic relations. This is done by assigning category and sentiment of the medical concepts and contexts. The categories considered in this research, are diseases, symptoms, drugs, human_anatomy, and miscellaneous medical terms, whereas sentiments are considered as positive and negative. The proposed assignment systems are developed on the top of WordNet of Medical Event (WME) lexicon. The developed lexicon provides medical concepts and their features, namely Parts-Of-Speech (POS), gloss (descriptive explanation), Similar Sentiment Words (SSW), affinity score, gravity score, polarity score, and sentiment. Several well-known supervised classifiers, including Naive Bayes, Logistic Regression, and support vector-based Sequential Minimal Optimization (SMO) have been applied to evaluate the developed systems. The proposed approaches have resulted in a concepts clustering application by identifying the semantic relations of concepts. The application provides potential exploitation in several domains, such as medical ontologies and recommendation systems.

Research of Clinical Named Entity Recognition Based on Bi-LSTM-CRF

Electronic Medical Records (EMR) with unstructured sentences and various conceptual expressions provide rich information for medical information extraction. However, common Named Entity Recognition (NER) in Natural Language Processing (NLP) are not well suitable for clinical NER in EMR. This study aims at applying neural networks to clinical concept extractions. We integrate Bidirectional Long Short-Term Memory Networks (Bi-LSTM) with a Conditional Random Fields (CRF) layer to detect three types of clinical named entities. Word representations fed into the neural networks are concatenated by character-based word embeddings and Continuous Bag of Words (CBOW) embeddings trained both on domain and non-domain corpus. We test our NER system on i2b2/VA open datasets and compare the performance with six related works, achieving the best result of NER with F1 value 0.853 7. We also point out a few specific problems in clinical concept extractions which will give some hints to deeper studies.

Cross-domain graph based similarity measurement of workflows

The aim of this article is to analyze search and retrieval of workflows. It represents workflows relatedness based on transfer learning. Workflows from different domains (e.g. scientific or business) have similarities and, more important, differences between themselves. Some concepts and solutions developed in one domain may be readily applicable to the other. This paper proposes a cross-domain concept extraction by similarity measurement and has a new research effort at the intersection of workflow domains. It deals with the huge amount of structured and unstructured data (Big Data) that is a demanding task when working on real-life event logs. The proposed method in this paper gives a general solution in the sense that it can be coupled to any Process Aware Information System.

Key Concept Identification: A Comprehensive Analysis of Frequency and Topical Graph-Based Approaches

Automatic key concept extraction from text is the main challenging task in information extraction, information retrieval and digital libraries, ontology learning, and text analysis. The statistical frequency and topical graph-based ranking are the two kinds of potentially powerful and leading unsupervised approaches in this area, devised to address the problem. To utilize the potential of these approaches and improve key concept identification, a comprehensive performance analysis of these approaches on datasets from different domains is needed. The objective of the study presented in this paper is to perform a comprehensive empirical analysis of selected frequency and topical graph-based algorithms for key concept extraction on three different datasets, to identify the major sources of error in these approaches. For experimental analysis, we have selected TF-IDF, KP-Miner and TopicRank. Three major sources of error, i.e., frequency errors, syntactical errors and semantical errors, and the factors that contribute to these errors are identified. Analysis of the results reveals that performance of the selected approaches is significantly degraded by these errors. These findings can help us develop an intelligent solution for key concept extraction in the future.

Ad Hoc Information Extraction for Clinical Data Warehouses.

Summary Background: Clinical Data Warehouses (CDW) reuse Electronic health records (EHR) to make their data retrievable for research purposes or patient recruitment for clinical trials. However, much information are hidden in unstructured data like discharge letters. They can be preprocessed and converted to structured data via information extraction (IE), which is unfortunately a laborious task and therefore usually not available for most of the text data in CDW. Objectives: The goal of our work is to provide an ad hoc IE service that allows users to query text data ad hoc in a manner similar to querying structured data in a CDW. While search engines just return text snippets, our systems also returns frequencies (e.g. how many patients exist with “heart failure” including textual synonyms or how many patients have an LVEF < 45) based on the content of discharge letters or textual reports for special investigations like heart echo. Three subtasks are addressed: (1) To recognize and to exclude negations and their scopes, (2) to extract concepts, i.e. Boolean values and (3) to extract numerical values. Methods: We implemented an extended version of the NegEx-algorithm for German texts that detects negations and determines their scope. Furthermore, our document oriented CDW PaDaWaN was extended with query functions, e.g. context sensitive queries and regex queries, and an extraction mode for computing the frequencies for Boolean and numerical values. Results: Evaluations in chest X-ray reports and in discharge letters showed high F1-scores for the three subtasks: Detection of negated concepts in chest X-ray reports with an F1-score of 0.99 and in discharge letters with 0.97; of Boolean values in chest X-ray reports about 0.99, and of numerical values in chest X-ray reports and discharge letters also around 0.99 with the exception of the concept age. Discussion: The advantages of an ad hoc IE over a standard IE are the low development effort (just entering the concept with its variants), the promptness of the results and the adaptability by the user to his or her particular question. Disadvantage are usually lower accuracy and confidence. This ad hoc information extraction approach is novel and exceeds existing systems: Roogle [ 1 ] extracts predefined concepts from texts at preprocessing and makes them retrievable at runtime. Dr. Warehouse [ 2 ] applies negation detection and indexes the produced subtexts which include affirmed findings. Our approach combines negation detection and the extraction of concepts. But the extraction does not take place during preprocessing, but at runtime. That provides an ad hoc, dynamic, interactive and adjustable information extraction of random concepts and even their values on the fly at runtime. Conclusions: We developed an ad hoc information extraction query feature for Boolean and numerical values within a CDW with high recall and precision based on a pipeline that detects and removes negations and their scope in clinical texts.

Single Term Concepts from English Translated Qur’an Using Statistical Methods

Ontology is essential for the success of knowledge based systems because it has the opportunity to share vocabulary, integrate knowledge easily and discover new instances or relations. However, the development of ontology via manual is time consuming and tedious task. Thus, ontology learning comes to play it roles. The ontology learning tries to extract ontological elements to support the ontology development. Concept extraction is one of the important tasks in ontology learning. The Hajj domain of Quranic study, concepts have not fully discovered. Hence, this paper tries to discover concepts by extracting the single terms from Qur’an translated version. It provides result on extracting the single terms as concepts by using statistical methods. Apart from that, it has been experimented for English Translated Quran by Hilali Khan. Result shows that the performance of using tf method as a statistical method is significant with the f-measure value is 0.509. Based on the tf, the comparisons have been made for other statistical methods such as tfidf, Avetf and Ridf.

Accelerating annotation of articles via automated approaches: evaluation of the neXtA5 curation-support tool by neXtProt.

The development of efficient text-mining tools promises to boost the curation workflow by significantly reducing the time needed to process the literature into biological databases. We have developed a curation support tool, neXtA5, that provides a search engine coupled with an annotation system directly integrated into a biocuration workflow. neXtA5 assists curation with modules optimized for the thevarious curation tasks: document triage, entity recognition and information extraction.Here, we describe the evaluation of neXtA5 by expert curators. We first assessed the annotations of two independent curators to provide a baseline for comparison. To evaluate the performance of neXtA5, we submitted requests and compared the neXtA5 results with the manual curation. The analysis focuses on the usability of neXtA5 to support the curation of two types of data: biological processes (BPs) and diseases (Ds). We evaluated the relevance of the papers proposed as well as the recall and precision of the suggested annotations.The evaluation of document triage by neXtA5 precision showed that both curators agree with neXtA5 for 67 (BP) and 63% (D) of abstracts, while curators agree on accepting or rejecting an abstract ~80% of the time. Hence, the precision of the triage system is satisfactory.For concept extraction, curators approved 35 (BP) and 25% (D) of the neXtA5 annotations. Conversely, neXtA5 successfully annotated up to 36 (BP) and 68% (D) of the terms identified by curators. The user feedback obtained in these tests highlighted the need for improvement in the ranking function of neXtA5 annotations. Therefore, we transformed the information extraction component into an annotation ranking system. This improvement results in a top precision (precision at first rank) of 59 (D) and 63% (BP). These results suggest that when considering only the first extracted entity, the current system achieves a precision comparable with expert biocurators.

A New Model of Corporate Sports from a Human Resources Management Perspective: Concept Extraction from a Case Study of Employment by Athnavi

A New Model of Corporate Sports from a Human Resources Management Perspective: Concept Extraction from a Case Study of Employment by Athnavi

Automatic Extraction of Learning Concepts from Exam Query Repositories

Educational data mining (or EDM) is an emerging interdisciplinary research field concerned with developing methods for exploring the specific and diverse data encountered in the field of education. One of the most valuable data sources in the educational domain are exam query repositories, which are commonly pre-dating modern e-learning systems. Exam queries in those repositories usually lack additional metadata which helps establish relationships between questions and corresponding learning concepts whose adoption is being tested. In this paper we present our novel approach of using data mining methods able to automatically annotate pre-existing exam queries with information about learning concepts they relate to, leveraging both textual and visual information contained in the queries. This enables automatic categorization of exam queries which allows for both better insight into the usability of the current exam query corpus as well as easier reporting of learning concept adoption after these queries are used in exams. We apply this approach to real-life exam questions from a high education university course and show validation of our results performed in consultation with experts from the educational domain.

Efficient Reduction of Overgeneration Errors for Automatic Controlled Indexing with an Application to the Biomedical Domain

Studies on MetaMap and MaxMatcher has shown that both concept extraction systems suffer from overgeneration problems. Over-generation occurs when the extraction systems mistakenly select an irrelevant concept. One of the reasons for these errors is that these systems use the words to weight the terms of the concepts. In this paper, an Integer Linear Programming model is used to select the optimal subset of extracted concept mentions covering the largest number of important words in the document to be indexed. Then each concept mentions that this set is mapped to a unique concept in UMLS using an information retrieval model.

Fundamental study on design concept extraction by neural network from a set of design alternatives

Fundamental study on design concept extraction by neural network from a set of design alternatives

Assisting document triage for human kinome curation via machine learning.

In the era of data explosion, the increasing frequency of published articles presents unorthodox challenges to fulfill specific curation requirements for bio-literature databases. Recognizing these demands, we designed a document triage system with automatic methods that can improve efficiency to retrieve the most relevant articles in curation workflows and reduce workloads for biocurators. Since the BioCreative VI (2017), we have implemented texting mining processing in our system in hopes of providing higher effectiveness for curating articles related to human kinase proteins. We tested several machine learning methods together with state-of-the-art concept extraction tools. For features, we extracted rich co-occurrence and linguistic information to model the curation process of human kinome articles by the neXtProt database. As shown in the official evaluation on the human kinome curation task in BioCreative VI, our system can effectively retrieve 5.2 and 6.5 kinase articles with the relevant disease (DIS) and biological process (BP) information, respectively, among the top 100 returned results. Comparing to neXtA5, our system demonstrates significant improvements in prioritizing kinome-related articles as follows: our system achieves 0.458 and 0.109 for the DIS axis whereas the neXtA5’s best-reported mean average precision (MAP) and maximum precision observed are 0.41 and 0.04. Our system also outperforms the neXtA5 in retrieving BP axis with 0.195 for MAP and the neXtA5’s reported value was 0.11. These results suggest that our system may be able to assist neXtProt biocurators in practice.

KnowEdu: A System to Construct Knowledge Graph for Education

Motivated by the vast applications of knowledge graph and the increasing demand in education domain, we propose a system, called KnowEdu, to automatically construct knowledge graph for education. By leveraging on heterogeneous data (e.g., pedagogical data and learning assessment data) from the education domain, this system first extracts the concepts of subjects or courses and then identifies the educational relations between the concepts. More specifically, it adopts the neural sequence labeling algorithm on pedagogical data to extract instructional concepts and employs probabilistic association rule mining on learning assessment data to identify the relations with educational significance. We detail all the above mentioned efforts through an exemplary case of constructing a demonstrative knowledge graph for mathematics, where the instructional concepts and their prerequisite relations are derived from curriculum standards and concept-based performance data of students. Evaluation results show that the F1 score for concept extraction exceeds 0.70, and for relation identification, the area under the curve and mean average precision achieve 0.95 and 0.87, respectively.

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition

BackgroundPrevious state-of-the-art systems on Drug Name Recognition (DNR) and Clinical Concept Extraction (CCE) have focused on a combination of text “feature engineering” and conventional machine learning algorithms such as conditional random fields and support vector machines. However, developing good features is inherently heavily time-consuming. Conversely, more modern machine learning approaches such as recurrent neural networks (RNNs) have proved capable of automatically learning effective features from either random assignments or automated word “embeddings”. Objectives(i) To create a highly accurate DNR and CCE system that avoids conventional, time-consuming feature engineering. (ii) To create richer, more specialized word embeddings by using health domain datasets such as MIMIC-III. (iii) To evaluate our systems over three contemporary datasets. MethodsTwo deep learning methods, namely the Bidirectional LSTM and the Bidirectional LSTM-CRF, are evaluated. A CRF model is set as the baseline to compare the deep learning systems to a traditional machine learning approach. The same features are used for all the models. ResultsWe have obtained the best results with the Bidirectional LSTM-CRF model, which has outperformed all previously proposed systems. The specialized embeddings have helped to cover unusual words in DrugBank and MedLine, but not in the i2b2/VA dataset. ConclusionsWe present a state-of-the-art system for DNR and CCE. Automated word embeddings has allowed us to avoid costly feature engineering and achieve higher accuracy. Nevertheless, the embeddings need to be retrained over datasets that are adequate for the domain, in order to adequately cover the domain-specific vocabulary.

Knowledge Management Framework for Emerging Infectious Diseases Preparedness and Response: Design and Development of Public Health Document Ontology.

BackgroundThere are increasing concerns about our preparedness and timely coordinated response across the globe to cope with emerging infectious diseases (EIDs). This poses practical challenges that require exploiting novel knowledge management approaches effectively.ObjectiveThis work aims to develop an ontology-driven knowledge management framework that addresses the existing challenges in sharing and reusing public health knowledge.MethodsWe propose a systems engineering-inspired ontology-driven knowledge management approach. It decomposes public health knowledge into concepts and relations and organizes the elements of knowledge based on the teleological functions. Both knowledge and semantic rules are stored in an ontology and retrieved to answer queries regarding EID preparedness and response.ResultsA hybrid concept extraction was implemented in this work. The quality of the ontology was evaluated using the formal evaluation method Ontology Quality Evaluation Framework.ConclusionsOur approach is a potentially effective methodology for managing public health knowledge. Accuracy and comprehensiveness of the ontology can be improved as more knowledge is stored. In the future, a survey will be conducted to collect queries from public health practitioners. The reasoning capacity of the ontology will be evaluated using the queries and hypothetical outbreaks. We suggest the importance of developing a knowledge sharing standard like the Gene Ontology for the public health domain.

Технологія екстрагування нових подій за визначеною тематикою із соціальної мережі Twitter

It is presented an overview of our approach to information extraction, which is a field of natural language processing that deals with new events from Twitter social network. There are formed methods and approaches into technology for detection events and determine their novelty. On the main base of our approach we offered to use technology of extracting events based on special dictionaries with event triggers, event classification event or not event by the method of classification of naive Bayes and extraction of special concepts and analysis their duplication with past events in some database of events. The approaches and algorithms of the technology based on these methods are presented. There is a steady interest in effective event extraction, due to its conceptual simplicity from one hand, and its potential utility on the other. The task of processing natural language has many problems, some of which cannot be solved within the framework of this technology, but the solution of which could improve the effectiveness of detecting new events.

Extracting Conceptual Relationships and Inducing Concept Lattices from Unstructured Text

Abstract Concept and relationship extraction from unstructured text data plays a key role in meaning aware computing paradigms, which make computers intelligent by helping them learn, interpret, and synthesis information. These concepts and relationships leverage knowledge in the form of ontological structures, which is the backbone of semantic web. This paper proposes a framework that extracts concepts and relationships from unstructured text data and then learns lattices that connect concepts and relationships. The proposed framework uses an off-the-shelf tool for identifying common concepts from a plain text corpus and then implements machine learning algorithms for classifying common relations that connect those concepts. Formal concept analysis is then used for generating concept lattices, which is a proven and principled method of creating formal ontologies that aid machines to learn things. A rigorous and structured experimental evaluation of the proposed method on real-world datasets has been conducted. The results show that the newly proposed framework outperforms state-of-the-art approaches in concept extraction and lattice generation.

Concept Extraction Based on Hybrid Approach Combined with Semantic Analysis

This paper proposed a hybrid approach for concept extraction, which combined linguistic, statistical and semantic analyses. Similar to traditional methods, linguistic and statistical analyses were reserved; this paper innovatively adopted semantic analysis to analyze the semantic relationships of concepts in order to get a fine grained result. Another creative work is the combination of several statistical approaches from different perspective to filter the candidate concepts. Experiments had shown a promising result.

Learning domain taxonomies: the TaxoLine approach

PurposeThe aim of this paper is to present an online framework for building a domain taxonomy, called TaxoLine, from Web documents automatically.Design/methodology/approachTaxoLine proposes an innovative methodology that combines frequency and conditional mutual information to improve the quality of the domain taxonomy. The system also includes a set of mechanisms that improve the execution time needed to build the ontology.FindingsThe performance of the TaxoLine framework was applied to nine different financial corpora. The generated taxonomies are evaluated against a gold-standard ontology and are compared to state-of-the-art ontology learning methods.Originality/valueThe experimental results show that TaxoLine produces high precision and recall for both concept and relation extraction than well-known ontology learning algorithms. Furthermore, it also shows promising results in terms of execution time needed to build the domain taxonomy.

Active learning reduces annotation time for clinical concept extraction

ObjectiveTo investigate: (1) the annotation time savings by various active learning query strategies compared to supervised learning and a random sampling baseline, and (2) the benefits of active learning-assisted pre-annotations in accelerating the manual annotation process compared to de novo annotation. Materials and methodsThere are 73 and 120 discharge summary reports provided by Beth Israel institute in the train and test sets of the concept extraction task in the i2b2/VA 2010 challenge, respectively. The 73 reports were used in user study experiments for manual annotation. First, all sequences within the 73 reports were manually annotated from scratch. Next, active learning models were built to generate pre-annotations for the sequences selected by a query strategy. The annotation/reviewing time per sequence was recorded. The 120 test reports were used to measure the effectiveness of the active learning models. ResultsWhen annotating from scratch, active learning reduced the annotation time up to 35% and 28% compared to a fully supervised approach and a random sampling baseline, respectively. Reviewing active learning-assisted pre-annotations resulted in 20% further reduction of the annotation time when compared to de novo annotation. DiscussionThe number of concepts that require manual annotation is a good indicator of the annotation time for various active learning approaches as demonstrated by high correlation between time rate and concept annotation rate. ConclusionActive learning has a key role in reducing the time required to manually annotate domain concepts from clinical free text, either when annotating from scratch or reviewing active learning-assisted pre-annotations.