Natural Language Processing Model for Automatic Analysis of Cybersecurity-Related Documents

This paper describes the development and implementation of a natural language processing model based on machine learning which performs cognitive analysis for cybersecurity-related documents. A domain ontology was developed using a two-step approach: (1) the symmetry stage and (2) the machine adjustment. The first stage is based on the symmetry between the way humans represent a domain and the way machine learning solutions do. Therefore, the cybersecurity field was initially modeled based on the expertise of cybersecurity professionals. A dictionary of relevant entities was created; the entities were classified into 29 categories and later implemented as classes in a natural language processing model based on machine learning. After running successive performance tests, the ontology was remodeled from 29 to 18 classes. Using the ontology, a natural language processing model based on a supervised learning model was defined. We trained the model using sets of approximately 300,000 words. Remarkably, our model obtained an F1 score of 0.81 for named entity recognition and 0.58 for relation extraction, showing superior results compared to other similar models identified in the literature. Furthermore, in order to be easily used and tested, a web application that integrates our model as the core component was developed.

Download Full-text

Obtaining Knowledge in Pathology Reports Through a Natural Language Processing Approach With Classification, Named-Entity Recognition, and Relation-Extraction Heuristics

JCO Clinical Cancer Informatics ◽

10.1200/cci.19.00008 ◽

2019 ◽

pp. 1-8 ◽

Cited By ~ 2

Author(s):

Tomasz Oliwa ◽

Steven B. Maron ◽

Leah M. Chase ◽

Samantha Lomnicki ◽

Daniel V.T. Catenacci ◽

...

Keyword(s):

Machine Learning ◽

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Named Entity Recognition ◽

Entity Recognition ◽

Classification Model ◽

Supervised Machine Learning ◽

Named Entity ◽

Pathology Reports

PURPOSE Robust institutional tumor banks depend on continuous sample curation or else subsequent biopsy or resection specimens are overlooked after initial enrollment. Curation automation is hindered by semistructured free-text clinical pathology notes, which complicate data abstraction. Our motivation is to develop a natural language processing method that dynamically identifies existing pathology specimen elements necessary for locating specimens for future use in a manner that can be re-implemented by other institutions. PATIENTS AND METHODS Pathology reports from patients with gastroesophageal cancer enrolled in The University of Chicago GI oncology tumor bank were used to train and validate a novel composite natural language processing-based pipeline with a supervised machine learning classification step to separate notes into internal (primary review) and external (consultation) reports; a named-entity recognition step to obtain label (accession number), location, date, and sublabels (block identifiers); and a results proofreading step. RESULTS We analyzed 188 pathology reports, including 82 internal reports and 106 external consult reports, and successfully extracted named entities grouped as sample information (label, date, location). Our approach identified up to 24 additional unique samples in external consult notes that could have been overlooked. Our classification model obtained 100% accuracy on the basis of 10-fold cross-validation. Precision, recall, and F1 for class-specific named-entity recognition models show strong performance. CONCLUSION Through a combination of natural language processing and machine learning, we devised a re-implementable and automated approach that can accurately extract specimen attributes from semistructured pathology notes to dynamically populate a tumor registry.

Download Full-text

DeNERT-KG: Named Entity and Relation Extraction Model Using DQN, Knowledge Graph, and BERT

Applied Sciences ◽

10.3390/app10186429 ◽

2020 ◽

Vol 10 (18) ◽

pp. 6429

Author(s):

SungMin Yang ◽

SoYeop Yoo ◽

OkRan Jeong

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Language Model ◽

Named Entity Recognition ◽

Relation Extraction ◽

Entity Recognition ◽

Knowledge Graph ◽

Named Entity ◽

Artificial Intelligence Technology

Along with studies on artificial intelligence technology, research is also being carried out actively in the field of natural language processing to understand and process people’s language, in other words, natural language. For computers to learn on their own, the skill of understanding natural language is very important. There are a wide variety of tasks involved in the field of natural language processing, but we would like to focus on the named entity registration and relation extraction task, which is considered to be the most important in understanding sentences. We propose DeNERT-KG, a model that can extract subject, object, and relationships, to grasp the meaning inherent in a sentence. Based on the BERT language model and Deep Q-Network, the named entity recognition (NER) model for extracting subject and object is established, and a knowledge graph is applied for relation extraction. Using the DeNERT-KG model, it is possible to extract the subject, type of subject, object, type of object, and relationship from a sentence, and verify this model through experiments.

Download Full-text

Advancing the State of the Art in Clinical Natural Language Processing through Shared Tasks

Yearbook of Medical Informatics ◽

10.1055/s-0038-1667079 ◽

2018 ◽

Vol 27 (01) ◽

pp. 184-192 ◽

Cited By ~ 5

Author(s):

Michele Filannino ◽

Özlem Uzuner

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Named Entity Recognition ◽

Relation Extraction ◽

Entity Recognition ◽

Data Driven ◽

Clear Trend ◽

Named Entity ◽

Clinical Natural Language Processing

Objectives: To review the latest scientific challenges organized in clinical Natural Language Processing (NLP) by highlighting the tasks, the most effective methodologies used, the data, and the sharing strategies. Methods: We harvested the literature by using Google Scholar and PubMed Central to retrieve all shared tasks organized since 2015 on clinical NLP problems on English data. Results: We surveyed 17 shared tasks. We grouped the data into four types (synthetic, drug labels, social data, and clinical data) which are correlated with size and sensitivity. We found named entity recognition and classification to be the most common tasks. Most of the methods used to tackle the shared tasks have been data-driven. There is homogeneity in the methods used to tackle the named entity recognition tasks, while more diverse solutions are investigated for relation extraction, multi-class classification, and information retrieval problems. Conclusions: There is a clear trend in using data-driven methods to tackle problems in clinical NLP. The availability of more and varied data from different institutions will undoubtedly lead to bigger advances in the field, for the benefit of healthcare as a whole.

Download Full-text

Probing Patient Messages Enhanced by Natural Language Processing: A Top-Down Message Corpus Analysis

Health Data Science ◽

10.34133/2021/1504854 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

George Mastorakos ◽

Aditya Khurana ◽

Ming Huang ◽

Sunyang Fu ◽

Ahmad P. Tafti ◽

...

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Named Entity Recognition ◽

Corpus Analysis ◽

Entity Recognition ◽

Message Content ◽

Named Entity ◽

Medical Concepts ◽

Insight Into

Background. Patients increasingly use asynchronous communication platforms to converse with care teams. Natural language processing (NLP) to classify content and automate triage of these messages has great potential to enhance clinical efficiency. We characterize the contents of a corpus of portal messages generated by patients using NLP methods. We aim to demonstrate descriptive analyses of patient text that can contribute to the development of future sophisticated NLP applications. Methods. We collected approximately 3,000 portal messages from the cardiology, dermatology, and gastroenterology departments at Mayo Clinic. After labeling these messages as either Active Symptom, Logistical, Prescription, or Update, we used NER (named entity recognition) to identify medical concepts based on the UMLS library. We hierarchically analyzed the distribution of these messages in terms of departments, message types, medical concepts, and keywords therewithin. Results. Active Symptom and Logistical content types comprised approximately 67% of the message cohort. The “Findings” medical concept had the largest number of keywords across all groupings of content types and departments. “Anatomical Sites” and “Disorders” keywords were more prevalent in Active Symptom messages, while “Drugs” keywords were most prevalent in Prescription messages. Logistical messages tended to have the lower proportions of “Anatomical Sites,”, “Disorders,”, “Drugs,”, and “Findings” keywords when compared to other message content types. Conclusions. This descriptive corpus analysis sheds light on the content and foci of portal messages. The insight into the content and differences among message themes can inform the development of more robust NLP models.

Download Full-text

EventEpi–A Natural Language Processing Framework for Event-Based Surveillance

10.1101/19006395 ◽

2019 ◽

Author(s):

Auss Abbood ◽

Alexander Ullrich ◽

Rüdiger Busche ◽

Stéphane Ghozzi

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Web Application ◽

Fine Tuning ◽

Entity Recognition ◽

World Health ◽

Support Vector ◽

Event Based ◽

Processing Framework

AbstractAccording to the World Health Organization (WHO), around 60% of all outbreaks are detected using informal sources. In many public health institutes, including the WHO and the Robert Koch Institute (RKI), dedicated groups of epidemiologists sift through numerous articles and newsletters to detect relevant events. This media screening is one important part of event-based surveillance (EBS). Reading the articles, discussing their relevance, and putting key information into a database is a time-consuming process. To support EBS, but also to gain insights into what makes an article and the event it describes relevant, we developed a natural-language-processing framework for automated information extraction and relevance scoring. First, we scraped relevant sources for EBS as done at RKI (WHO Disease Outbreak News and ProMED) and automatically extracted the articles’ key data: disease, country, date, and confirmed-case count. For this, we performed named entity recognition in two steps: EpiTator, an open-source epidemiological annotation tool, suggested many different possibilities for each. We trained a naive Bayes classifier to find the single most likely one using RKI’s EBS database as labels. Then, for relevance scoring, we defined two classes to which any article might belong: The article is relevant if it is in the EBS database and irrelevant otherwise. We compared the performance of different classifiers, using document and word embeddings. Two of the tested algorithms stood out: The multilayer perceptron performed best overall, with a precision of 0.19, recall of 0.50, specificity of 0.89, F1 of 0.28, and the highest tested index balanced accuracy of 0.46. The support-vector machine, on the other hand, had the highest recall (0.88) which can be of higher interest for epidemiologists. Finally, we integrated these functionalities into a web application called EventEpi where relevant sources are automatically analyzed and put into a database. The user can also provide any URL or text, that will be analyzed in the same way and added to the database. Each of these steps could be improved, in particular with larger labeled datasets and fine-tuning of the learning algorithms. The overall framework, however, works already well and can be used in production, promising improvements in EBS. The source code is publicly available at https://github.com/aauss/EventEpi.

Download Full-text

Sentiment Analysis on Twitter Airline Data

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.35807 ◽

2021 ◽

Vol 9 (VI) ◽

pp. 3767-3770

Author(s):

Kirti Jain

Keyword(s):

Machine Learning ◽

Natural Language Processing ◽

Natural Language ◽

Sentiment Analysis ◽

Language Processing ◽

Learning Task ◽

Model Based ◽

Sentiment Mining ◽

General Opinion

Sentiment analysis, also known as sentiment mining, is a submachine learning task where we want to determine the overall sentiment of a particular document. With machine learning and natural language processing (NLP), we can extract the information of a text and try to classify it as positive, neutral, or negative according to its polarity. In this project, We are trying to classify Twitter tweets into positive, negative, and neutral sentiments by building a model based on probabilities. Twitter is a blogging website where people can quickly and spontaneously share their feelings by sending tweets limited to 140 characters. Because of its use of Twitter, it is a perfect source of data to get the latest general opinion on anything.

Download Full-text

Advances in Computational Linguistics and Text Processing Frameworks

Advances in Computer and Electrical Engineering - Handbook of Research on Engineering Innovations and Technology Management in Organizations ◽

10.4018/978-1-7998-2772-6.ch012 ◽

2020 ◽

pp. 217-244

Author(s):

Ayush Srivastav ◽

Hera Khan ◽

Amit Kumar Mishra

Keyword(s):

Neural Networks ◽

Natural Language Processing ◽

Natural Language ◽

Computational Linguistics ◽

Language Processing ◽

Text Processing ◽

Named Entity Recognition ◽

Entity Recognition ◽

Named Entity ◽

Part Of Speech

The chapter provides an eloquent account of the major methodologies and advances in the field of Natural Language Processing. The most popular models that have been used over time for the task of Natural Language Processing have been discussed along with their applications in their specific tasks. The chapter begins with the fundamental concepts of regex and tokenization. It provides an insight to text preprocessing and its methodologies such as Stemming and Lemmatization, Stop Word Removal, followed by Part-of-Speech tagging and Named Entity Recognition. Further, this chapter elaborates the concept of Word Embedding, its various types, and some common frameworks such as word2vec, GloVe, and fastText. A brief description of classification algorithms used in Natural Language Processing is provided next, followed by Neural Networks and its advanced forms such as Recursive Neural Networks and Seq2seq models that are used in Computational Linguistics. A brief description of chatbots and Memory Networks concludes the chapter.

Download Full-text

OP41 Intercultural Medical Decision Support System Using Natural Language Processing (NLP)

International Journal of Technology Assessment in Health Care ◽

10.1017/s0266462319001090 ◽

2019 ◽

Vol 35 (S1) ◽

pp. 10-10

Author(s):

Merve Gökgöl ◽

Zeynep Orhan

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Named Entity Recognition ◽

Similarity Score ◽

Entity Recognition ◽

Medical Decision ◽

Similarity Function ◽

String Similarity ◽

Relevant Today

IntroductionThis study aimed to reach patients using different languages while providing an opportunity to enter symptoms in their everyday language text besides medical expressions of symptoms.MethodologyNamed entity recognition (NER) techniques, based on natural language processing (NLP), were applied to develop a language independent predictive model. The research was based on extracting symptoms entered to the system by patient using NER method of NLP. In order to implement the system, python was used while pre-processing the data and string similarity function was used to estimate similarity with disease symptoms. Two sets were used for classification, one including only symptoms, and the other the matching diseases. Four thousand two hundred and eighty different symptoms were processed for the corresponding 880 diseases.ResultsEach user symptom had a similarity score for each symptom in all diseases. Top N results with highest similarities were chosen from this list. The final N results are matched with diseases. According to these results, matched diseases were ordered in terms of the percentage of matched symptoms in the disease's symptoms. Extracted terms were implied as an input of the model and analysed for a matching diagnosis where an accuracy of 83 percent was accomplished when it is tested and compared using Mayo Clinic data for specific foreign languages other than English.ConclusionThis language independent online diagnostic tool is a solution for both personal and clinical use and provides maintainable, updatable and more reliable diagnostics. This tool is particularly relevant today, with global mobility growing at a rate faster than the world`s population. We aim to upgrade the system by adding speech recognition and engaging it with the background (if available, electronic health records) of the patient.

Download Full-text