Information Extraction Approach Research Articles

An automatic histogram detection and information extraction from document images

Histogram is an important data chart that is commonly present in scientific documents. In this paper, an automatic histogram detection and information extraction methodology, based on Hough line detector and Morphological operator, is proposed. The proffered system is comprised of three steps: pre-processing, axis detection, and chart pattern extraction. In the pre-processing step, the RGB image pattern of a histogram is converted into a binary image. Next, in the axis detection step, horizontal axis, vertical axis and title of the histogram are extracted. In this step Hough line detector methodology was applied to detect horizontal and vertical lines in the image patterns. From the set of identified vertical lines, both the endpoints of a line, having the same minimum values of x co-ordinate was considered as a vertical axis. Similarly, from the set of identified horizontal lines, the two endpoints of a line having the same maximum values of y co-ordinate were considered as a horizontal axis. With respect to the dimensions of the horizontal axis and vertical axis, a rectangular region containing horizontal axis values and label, vertical axis values and label and title are extracted. In the final chart pattern extraction step, using morphological operations, the frequency of data present in the histogram was identified. Verification and validation tests of the propounded system yielded promising results, indicative of efficient approach for extraction of histogram information.

A Methodology for Open Information Extraction and Representation from Large Scientific Corpora: The CORD-19 Data Exploration Use Case

The usefulness of automated information extraction tools in generating structured knowledge from unstructured and semi-structured machine-readable documents is limited by challenges related to the variety and intricacy of the targeted entities, the complex linguistic features of heterogeneous corpora, and the computational availability for readily scaling to large amounts of text. In this paper, we argue that the redundancy and ambiguity of subject–predicate–object (SPO) triples in open information extraction systems has to be treated as an equally important step in order to ensure the quality and preciseness of generated triples. To this end, we propose a pipeline approach for information extraction from large corpora, encompassing a series of natural language processing tasks. Our methodology consists of four steps: i. in-place coreference resolution, ii. extractive text summarization, iii. parallel triple extraction, and iv. entity enrichment and graph representation. We manifest our methodology on a large medical dataset (CORD-19), relying on state-of-the-art tools to fulfil the aforementioned steps and extract triples that are subsequently mapped to a comprehensive ontology of biomedical concepts. We evaluate the effectiveness of our information extraction method by comparing it in terms of precision, recall, and F1-score with state-of-the-art OIE engines and demonstrate its capabilities on a set of data exploration tasks.

The Use of Ontology in Clinical Information Extraction

Extracting clinical data from medical or clinical reports is a crucial effort. These records contain the most valuable pieces of evidence of treatments in humans. Integration of information extraction (IE) and ontology can produce a great tool for clinical concept extraction. The aim of this paper is to present a quick overview of the research work which has applied IE and ontology approaches in medical or clinical concepts extraction. This paper also presents our proposed framework based on the integration of both approaches mentioned above for extracting clinical concepts.

A novel approach to extracting useful information from noisy TFDs using 2D local entropy measures

The paper proposes a novel approach for extraction of useful information and blind source separation of signal components from noisy data in the time-frequency domain. The method is based on the local Rényi entropy calculated inside adaptive, data-driven 2D regions, the sizes of which are calculated utilizing the improved, relative intersection of confidence intervals (RICI) algorithm. One of the advantages of the proposed technique is that it does not require any prior knowledge on the signal, its components, or noise, but rather the processing is performed on the noisy signal mixtures. Also, it is shown that the method is robust to the selection of time-frequency distributions (TFDs). It has been tested for different signal-to-noise-ratios (SNRs), both for synthetic and real-life data. When compared to fixed TFD thresholding, adaptive TFD thresholding based on RICI rule and the 1D entropy-based approach, the proposed adaptive method significantly increases classification accuracy (by up to 11.53%) and F1 score (by up to 7.91%). Hence, this adaptive, data-driven, entropy-based technique is an efficient tool for extracting useful information from noisy data in the time-frequency domain.

PragmaticOIE: a pragmatic open information extraction for Portuguese language

Information extraction (IE) involves the extraction of useful facts from texts. IE approaches have been categorized into two types: Traditional IE and Open IE. Traditional IE recognizes a predefined set of relationships between the arguments, and it has typically been applied to specific domains. Open IE extracts relationship descriptors expressing any semantic relationship between a pair of arguments in different domains. Although a sentence can have a different meaning, given the context and intention used, a single semantic analysis does not guarantee useful extractions. Extractions depend on the context and the intention inherited in a sentence that goes beyond the semantic meaning. Thus, a pragmatic analysis enhances the set of extractions by considering the contextual and intentional aspects. As a consequence, new facts can be extracted from this set of sentences. The combination of inference, context, and intention enables the extraction of implicit facts from texts achieving a first pragmatic level. This novel approach increases the number of facts, extracting relationships from a sentence analyzing inference, context, and intention. This is the first method to analyze a first pragmatic level from a sentence within a set of Portuguese text documents. Our method was performed over a set of Portuguese text documents and outperforms the most relevant related work comparing accuracy, number of extracted facts, and minimality measures.

A Near-Real-Time Answer Discovery for Open-Domain With Unanswerable Questions From the Web

With the proliferation of question and answering (Q&A) services, studies on building a knowledge base (KB) using various information extraction (IE) methodologies from unstructured data on the Web have received significant attention. Existing IE approaches, including machine reading comprehension (MRC), can find the correct answer to a question if the correct answer exists in the document. However, most are prone to extracting incorrect answers rather than producing no answers when the correct answer does not exist in the given documents. This problem is likely to cause serious real-world problems when we apply such technologies to practical services such as AI speakers. We propose a novel open-domain IE system to alleviate the weaknesses of previous approaches. The proposed system integrates an elaborated document selection, sentence selection, and knowledge extraction ensemble method to obtain high specificity while maintaining a realistically achievable level of precision. Based on this framework, we extract answers on Korean open-domain user queries from unstructured documents collected from multiple Web sources. For evaluating our system, we build a benchmark dataset with the SKTelecom AI Speaker log. The baseline models KYLIN infobox generator and BiDAF were used to evaluate the performance of the proposed approach. The experimental results demonstrate that the proposed method outperforms the baseline models and is practically applicable to real-world services.

Text Detection and Recognition for Images of Medical Laboratory Reports With a Deep Learning Approach

The adoption of electronic health records (EHRs) is an important step in the development of modern medicine. However, complete health records are not often available during treatment because of the functional problem of the EHR system or information barriers. This paper presents a deep-learning-based approach for textual information extraction from images of medical laboratory reports, which may help physicians solve the data-sharing problem. The approach consists of two modules: text detection and recognition. In text detection, a patch-based training strategy is applied, which can achieve the recall of 99.5% in the experiments. For text recognition, a concatenation structure is designed to combine the features from both shallow and deep layers in neural networks. The experimental results demonstrate that the text recognizer in our approach can improve the accuracy of multi-lingual text recognition. The approach will be beneficial for integrating historical health records and engaging patients in their own health care.

Named-Entity Recognition Using Automatic Construction of Training Data From Social Media Messaging Apps

In recent years, social media messaging app data has served as a precious resource to extract useful information, such as critical clues and evidence in legal trials and criminal investigations. Although these data can be of various types, they are mostly in the form of natural language text. Therefore, to extract information from them efficiently, it is essential to research practical natural language processing approaches. This study proposes applying a deep-learning-based named-entity recognition (NER) system as a natural language processing approach for information extraction to these messaging data. In addition, a system for automatically constructing NER training data is presented using the distant supervision method for the training data of deep-learning models. Because social media messaging app data generally include a significant amount of noise, such as typographical and word-spacing errors, a NER system with robustness against these types of noisy data is required to extract information from the messaging data effectively. The results demonstrate that the proposed approach outperforms that of a NER system with manually labeled training data.

Improved Spatial Information Based Semisupervised Classification of Remote Sensing Images

Motivation in the use of semisupervised learning method is because of its ability to strategically explore and use abundantly available unlabeled samples along with the limited number of labeled samples, as seen in the remote sensing (RS) imagery. In this direction, the present article proposes a semisupervised classification model with spatial information based self-learning methodology to classify land covers in RS images. The model uses granular neural network (GNN) as the base classifier because of its customizable network architecture that is functionally interpretable and costs less computational complexity. Architecture of GNN is governed by fuzzy if–then rules that are generated from fuzzy granulation of input feature space. We have used an improved spatial neighborhood learning method for better understanding of data distribution in a semisupervised framework. The method collects the information with collaborative opinions of two independent information extraction approaches, i.e., based on mutual neighborhood criteria and class map of unlabeled samples. Superiority of the proposed model with existing methods are established with different RS images in terms of various performance measurement indexes.

Semantically Explainable Fuzzy Classifier

In machine learning, there are many high-performance classifiers. However, because of lack of transparency, they are not able to explain the data in a human-friendly form. In this paper, Cumulative Fuzzy Class Membership Criterion (CFCMC), a recently proposed fuzzy modeling classifier, is modified and utilized for a novel approach of information extraction from the labeled data. This approach is able to explain the classifiability of the data in the form of semantics. Extracted semantics give information about the structure of the data and the similarities between classes. To get a relevant image of its classification performance, it is compared to three well-known and frequently used classifiers, which are considered as black boxes, namely, SVM, MLP, and kNN, and to a similar transparent approach, MF ARTMAP. To validate extracted semantics, they are compared to visualization of classified data and to confusion matrices generated during the evaluation of the created CFCMC models. The experimental result shows that CFCMC is not necessarily the best classifier, although, in most cases, it is not too far from the best performing methods. However, the semantical explanation potentially allows the classifier to be applied as a support for human decision processes in real-world problems.

Comparing information extraction techniques for low-prevalence concepts: The case of insulin rejection by patients.

To comparatively evaluate a range of Natural Language Processing (NLP) approaches for Information Extraction (IE) of low-prevalence concepts in clinical notes on the example of decline of insulin therapy recommendation by patients. We evaluated the accuracy of detection of documentation of decline of insulin therapy by patients using sentence-level naïve Bayes, logistic regression and support vector machine (SVM)-based classification (with and without SMOTE oversampling), token-level sequence labelling using conditional random fields (CRFs), uni- and bi-directional recurrent neural network (RNN) models with GRU and LSTM cells, and rule-based detection using Canary platform. All models were trained using the same manually annotated 50,046-document training set and evaluated on the same 1501-document held-out set. Hyperparameter optimization was performed using 10-fold cross-validation. At the sentence level, prevalence of documentation of decline of insulin therapy by patients was 0.02% in both training and held-out sets. Naïve Bayes and logistic regression models did not achieve F1 score ≥ 0.5 on the training set and were not further evaluated. Among the other models, evaluation against the held-out test set showed that SVM identified decline of insulin therapy by patients with F1 score of 0.61, CRF with F1 of 0.51, RNN with F1 of 0.67 and Canary rule-based model with F1 of 0.97. Identification of low-prevalence concepts can present challenges in medical language processing. Rule-based systems that include the designer's background knowledge of language may be able to achieve higher accuracy under these circumstances.

Deep Learning With Multiband Synthesis from Landsat-8 Satellite Imagery using Machine Learning

This examination article proposes a novel profound learning portrayal and division approach for moderate goals remote detecting picture investigation. An information extraction approach utilizing profound various leveled understanding for remote detecting picture is embraced as a proving ground for further increment in spatial goals symbolism. The thought is the way that we can receive a speedy filtering picture division in a profound learning highlight portrayal structure utilizing a profound learning method to deliver sensible measured bunches in portioned locales until it frames a super-object. Our commitment is to actualize a viable system for multi-scale picture investigation to address the issue of estimating vulnerability by and by. We at that point propose to test our strategy on two high goals remote detecting picture datasets that will yield brings about the type of multi-layered scenes that bear witness to the proficiency and unwavering quality of our proposed framework.

A novel text mining approach for scholar information extraction from web content in Chinese

Text mining is the process of deriving high-quality information from text so that it can focus on extracting useful information from text or web documents. IoT devices generate massive structured or unstructured data including text data. The opportunity coming behind big data and unstructured data is a great impulse for governments or companies to choose solutions based on text mining approaches to improve strategic business activities and boost decision making. Expert information is an important reference information for decision making. How to collect the expert information from text or web documents is a problem. In this paper, a text mining approach is introduced to crawl and extract expert information from Internet. We build a basic framework and main modules including information extraction, data cleaning and deduplication, expert recommendation model to cope with text data from Web content. We also define several metrics, data structures and propose some algorithms to help text mining. Finally, the experiment is implemented with datasets and the results show that our text mining approach can extract expert attributes accurately.

Data Mining Approach for Extraction of Useful Information About Biologically Active Compounds from Publications.

A lot of high quality data on the biological activity of chemical compounds are required throughout the whole drug discovery process: from development of computational models of the structure-activity relationship to experimental testing of lead compounds and their validation in clinics. Currently, a large amount of such data is available from databases, scientific publications, and patents. Biological data are characterized by incompleteness, uncertainty, and low reproducibility. Despite the existence of free and commercially available databases of biological activities of compounds, they usually lack unambiguous information about peculiarities of biological assays. On the other hand, scientific papers are the primary source of new data disclosed to the scientific community for the first time. In this study, we have developed and validated a data-mining approach for extraction of text fragments containing description of bioassays. We have used this approach to evaluate compounds and their biological activity reported in scientific publications. We have found that categorization of papers into relevant and irrelevant may be performed based on the machine-learning analysis of the abstracts. Text fragments extracted from the full texts of publications allow their further partitioning into several classes according to the peculiarities of bioassays. We demonstrate the applicability of our approach to the comparison of the endpoint values of biological activity and cytotoxicity of reference compounds.

An Online Spectral Information-Enhanced Approach for Artifact Detection and Fault Attentuation in Myoelectric Control.

In myocontrol of neuroprosthetic devices, multichannel electromyography (EMG) can be used to decode the intended motor command, based on distributed activation patterns of stump muscles. In this regard, the high density EMG (HD-EMG) approach allows for enhancement of the spatiotemporal resolution for motor intention detection. Despite the advantages of relying on several EMG channels, the challenge of high-density electrode systems is the dynamically changing electrode-skin contact impedance, which can affect a considerable number of electrodes over the time of data acquisition. This can result in obtaining unreliable, low-quality EMG recording with a distributed artifact pattern over the grid of EMG sensors. To address this issue, we propose a novel online approach for adaptive information extraction and enhancement for automatic artifact detection and attenuation in HD-EMG-based myocontrol of prosthetic devices. The method is based on an adaptive weighting scheme that modifies the contribution of each HD-EMG channel considering the spectral information content relative to artifacts. The technique (named IE-HD-EMG) was tested as an online pre-conditioning step for a challenging multiclass classification problem of 4-finger activation, using linear discriminant analysis. It is shown that for this application, the proposed IE-HD-EMG technique led to a superior performance in finger activation recognition (79.25% accuracy, 89% sensitivity, 89.15% specificity) in comparison to the conventional HD-EMG recording under the same condition without the proposed approach (56.25% accuracy, 61.3% sensitivity, 67% specificity). Therefore, the proposed technique can have a significant potential to expand the clinical viability of HD-EMG systems.

Solving Arithmetic Word Problems by Object Oriented Modeling and Query-Based Information Processing

The paper presents an Object Oriented Analysis and Design (OOAD) approach to modeling, reasoning and a database query based approach to processing and solving addition-subtraction (Add-Sub) type arithmetic Mathematical Word Problems (MWP) of elementary school level. The system identifies and extracts the key entities in a word problem like owners, items and their attributes and quantities, verbs, from all the input sentences, using a rule based Information Extraction (IE) approach based on Semantic Role Labeling (SRL) technique. These information are then stored in predefined templates which are further modeled to represent an MWP in the object-oriented paradigm and processed using query based approach to generate the answer. These kind of applications are based on Natural Language Processing (NLP), Natural Language Understanding (NLU) and Artificial Intelligence (AI), and can be used as intelligent dynamic mathematical tutoring tools as part of E-Learning systems, Learning Management Systems, on-line education, etc. The proposed object oriented mathematical word problem solver can solve arithmetic MWPs involving only addition-subtraction operations and it has produced an accuracy of 94.35% on a subset of the AI2 arithmetic questions dataset.

An approach for transgender population information extraction and summarization from clinical trial text

BackgroundGender information frequently exists in the eligibility criteria of clinical trial text as essential information for participant population recruitment. Particularly, current eligibility criteria text contains the incompleteness and ambiguity issues in expressing transgender population, leading to difficulties or even failure of transgender population recruitment in clinical trial studies.MethodsA new gender model is proposed for providing comprehensive transgender requirement specification. In addition, an automated approach is developed to extract and summarize gender requirements from unstructured text in accordance with the gender model. This approach consists of: 1) the feature extraction module, and 2) the feature summarization module. The first module identifies and extracts gender features using heuristic rules and automatically-generated patterns. The second module summarizes gender requirements by relation inference.ResultsBased on 100,134 clinical trials from ClinicalTrials.gov, our approach was compared with 20 commonly applied machine learning methods. It achieved a macro-averaged precision of 0.885, a macro-averaged recall of 0.871 and a macro-averaged F1-measure of 0.878. The results illustrated that our approach outperformed all baseline methods in terms of both commonly used metrics and macro-averaged metrics.ConclusionsThis study presented a new gender model aiming for specifying the transgender requirement more precisely. We also proposed an approach for gender information extraction and summarization from unstructured clinical text to enhance transgender-related clinical trial population recruitment. The experiment results demonstrated that the approach was effective in transgender criteria extraction and summarization.

Replicating medication trend studies using ad hoc information extraction in a clinical data warehouse

BackgroundMedication trend studies show the changes of medication over the years and may be replicated using a clinical Data Warehouse (CDW). Even nowadays, a lot of the patient information, like medication data, in the EHR is stored in the format of free text. As the conventional approach of information extraction (IE) demands a high developmental effort, we used ad hoc IE instead. This technique queries information and extracts it on the fly from texts contained in the CDW.MethodsWe present a generalizable approach of ad hoc IE for pharmacotherapy (medications and their daily dosage) presented in hospital discharge letters. We added import and query features to the CDW system, like error tolerant queries to deal with misspellings and proximity search for the extraction of the daily dosage. During the data integration process in the CDW, negated, historical and non-patient context data are filtered. For the replication studies, we used a drug list grouped by ATC (Anatomical Therapeutic Chemical Classification System) codes as input for queries to the CDW.ResultsWe achieve an F1 score of 0.983 (precision 0.997, recall 0.970) for extracting medication from discharge letters and an F1 score of 0.974 (precision 0.977, recall 0.972) for extracting the dosage. We replicated three published medical trend studies for hypertension, atrial fibrillation and chronic kidney disease. Overall, 93% of the main findings could be replicated, 68% of sub-findings, and 75% of all findings. One study could be completely replicated with all main and sub-findings.ConclusionA novel approach for ad hoc IE is presented. It is very suitable for basic medical texts like discharge letters and finding reports. Ad hoc IE is by definition more limited than conventional IE and does not claim to replace it, but it substantially exceeds the search capabilities of many CDWs and it is convenient to conduct replication studies fast and with high quality.

EVALUATION OF THE CLUSTERING PERFORMANCE OF AFFINITY PROPAGATION ALGORITHM CONSIDERING THE INFLUENCE OF PREFERENCE PARAMETER AND DAMPING FACTOR

Abstract: The identification of significant underlying data patterns such as image composition and spatial arrangements is fundamental in remote sensing tasks. Therefore, the development of an effective approach for information extraction is crucial to achieve this goal. Affinity propagation (AP) algorithm is a novel powerful technique with the ability of handling with unusual data, containing both categorical and numerical attributes. However, AP has some limitations related to the choice of initial preference parameter, occurrence of oscillations and processing of large data sets. This paper evaluates the clustering performance of AP algorithm taking into account the influence of preference parameter and damping factor. The study was conducted considering the AP algorithm, the adaptive AP and partition AP. According to the experiments, the choice of preference and damping greatly influences on the quality and the final number of clusters.

OpenIE-based approach for Knowledge Graph construction from text

Transforming unstructured text into a formal representation is an important goal of the Semantic Web in order to facilitate the integration and retrieval of information. The construction of Knowledge Graphs (KGs) pursues such an idea, where named entities (real world things) and their relations are extracted from text. In recent years, many approaches for the construction of KGs have been proposed by exploiting Discourse Analysis, Semantic Frames, or Machine Learning algorithms with existing Semantic Web data. Although such approaches are useful for processing taxonomies and connecting beliefs, they provide several linguistic descriptions, which lead to semantic data heterogeneity and thus, complicating data consumption. Moreover, Open Information Extraction (OpenIE) approaches have been slightly explored for the construction of KGs, which provide binary relations representing atomic units of information that could simplify the querying and representation of data. In this paper, we propose an approach to generate KGs using binary relations produced by an OpenIE approach. For such purpose, we present strategies for favoring the extraction and linking of named entities with KG individuals, and additionally, their association with grammatical units that lead to producing more coherent facts. We also provide decisions for selecting the extracted information elements for creating potentially useful RDF triples for the KG. Our results demonstrate that the integration of information extraction units with grammatical structures provides a better understanding of proposition-based representations provided by OpenIE for supporting the construction of KGs.