Information Extraction Approach Research Articles

CRMSP: A semi-supervised approach for key information extraction with Class-Rebalancing and Merged Semantic Pseudo-Labeling

CRMSP: A semi-supervised approach for key information extraction with Class-Rebalancing and Merged Semantic Pseudo-Labeling

A Bag-of-Words Approach for Information Extraction from Electricity Invoices

In the context of digitization and automation, extracting relevant information from business documents remains a significant challenge. It is typical to rely on machine-learning techniques to automate the process, reduce manual labor, and minimize errors. This work introduces a new model for extracting key values from electricity invoices, including customer data, bill breakdown, electricity consumption, or marketer data. We evaluate several machine learning techniques, such as Naive Bayes, Logistic Regression, Random Forests, or Support Vector Machines. Our approach relies on a bag-of-words strategy and custom-designed features tailored for electricity data. We validate our method on the IDSEM dataset, which includes 75,000 electricity invoices with eighty-six fields. The model converts PDF invoices into text and processes each word separately using a context of eleven words. The results of our experiments indicate that Support Vector Machines and Random Forests perform exceptionally well in capturing numerous values with high precision. The study also explores the advantages of our custom features and evaluates the performance of unseen documents. The precision obtained with Support Vector Machines is 91.86% on average, peaking at 98.47% for one document template. These results demonstrate the effectiveness of our method in accurately extracting key values from invoices.

Evaluation of machine learning algorithm capability for Bosten Lake Wetland classification based on multi-temporal Sentinel-2 data

As crucial carbon sinks within terrestrial ecosystems, wetlands have been extensively studied in terms of spatio-temporal distributions. However, existing methods for classifying wetlands are of limited accuracy, and it is difficult to acquire consistent samples over time. Therefore, precise classification methods are required to facilitate wetland conservation and ecological restoration. In this study, multiple machine learning (ML) algorithms in combination with feature sets based on Sentinel-2 data were used to accurately classify the land-use types (LUTs) of the Bosten Lake Wetland (BLW) in Xinjiang, China. The enhanced water index (EWI), modified normalised difference water index (MNDWI), and normalised difference water index (NDWI) were selected to extract water information and distinguish water bodies from land surfaces in the BLW. Three classification plans based on vegetation indices, water indices, and textural features were developed using artificial neural network (ANN), support vector machine (SVM), random forest (RF) algorithms. Plan 9 combined vegetation water and texture with the highest overall accuracy (OA) 91.02 % and kappa coefficient (KC) 0.89. This plan obtained a producer accuracy of over 90 % for lake wetlands, river wetlands, grassland wetlands, mud flats, and farmland and > 83 % for construction land and bareland. According to Plan 9, the wetland area during 2018–2023 showed noticeable seasonal fluctuations but stable interannual changes. Conversely, non-wetland areas demonstrated significant interannual fluctuations, particularly in bareland and farmland, which might have been influenced by urbanisation and ecological policies. This study provides insights into the data sources, feature selection, and methodological approaches for wetland information extraction in arid regions.

A scoping review of large language model based approaches for information extraction from radiology reports

Radiological imaging is a globally prevalent diagnostic method, yet the free text contained in radiology reports is not frequently used for secondary purposes. Natural Language Processing can provide structured data retrieved from these reports. This paper provides a summary of the current state of research on Large Language Model (LLM) based approaches for information extraction (IE) from radiology reports. We conduct a scoping review that follows the PRISMA-ScR guideline. Queries of five databases were conducted on August 1st 2023. Among the 34 studies that met inclusion criteria, only pre-transformer and encoder-based models are described. External validation shows a general performance decrease, although LLMs might improve generalizability of IE approaches. Reports related to CT and MRI examinations, as well as thoracic reports, prevail. Most common challenges reported are missing validation on external data and augmentation of the described methods. Different reporting granularities affect the comparability and transparency of approaches.

Deep learning approaches for information extraction from visually rich documents: datasets, challenges and methods

Deep learning approaches for information extraction from visually rich documents: datasets, challenges and methods

Multiview Classification Through Learning From Interval-Valued Data.

The classification problem concerning crisp-valued data has been well resolved. However, interval-valued data, where all of the observations' features are described by intervals, are also a common data type in real-world scenarios. For example, the data extracted by many measuring devices are not exact numbers but intervals. In this article, we focus on a highly challenging problem called learning from interval-valued data (LIND), where we aim to learn a classifier with high performance on interval-valued observations. First, we obtain the estimation error bound of the LIND problem based on the Rademacher complexity. Then, we give the theoretical analysis to show the strengths of multiview learning on classification problems, which inspires us to construct a new algorithm called multiview interval information extraction (Mv-IIE) approach for improving classification accuracy on interval-valued data. The experiment comparisons with several baselines on both synthetic and real-world datasets illustrate the superiority of the proposed framework in handling interval-valued data. Moreover, we describe an application of Mv-IIE that we can prevent data privacy leakage by transforming crisp-valued (raw) data into interval-valued data.

Machine Learning-Based System for Automated Presentation Generation from CSV Data

Effective presentation slides are crucial for conveying information efficiently, yet existing tools lack content analysis capabilities. This paper introduces a content-based PowerPoint presentation generator, aiming to address this gap. By leveraging automated techniques, slides are generated from text documents, ensuring original concepts are effectively communicated. Unstructured data poses challenges for organizations, impacting productivity and profitability. While traditional methods fall short, AI-based approaches offer promise. This systematic literature review (SLR) explores AI methods for extracting Data from unstructured details. Findings reveal limitations in existing methods, particularly in handling complex document layouts. Moreover, publicly available datasets are task-specific and of low quality, highlighting the need for comprehensive datasets reflecting real-world scenarios[1]. The SLR underscores the potential of Artificial-based approaches for information extraction but emphasizes the challenges in processing diverse document layouts. Proposed is a framework for constructing high-quality datasets and advocating for closer collaboration between businesses and researchers to address unstructured data challenges effectively.

Multimodal Geo-Information Extraction from Social Media for Supporting Decision-Making in Disaster Management

Abstract. Effective decision-making in natural disaster management relies heavily on a comprehensive understanding of the situation in affected areas. Social media has been established as a tool to monitor human response and damage assessment. Given the vast amounts of data available, computational methods such as topic modelling are typically employed to reduce information complexity. However, these methods mostly neglect aspects such as geographic location and emotional response, which frequently results in sequential workflows of initial semantic filtering and subsequent spatial or spatio-temporal analysis. This study presents a novel approach for multimodal information extraction from geo-social media data for aiding decision support in disaster management. The method leverages a spatial, temporal, semantic, and sentiment-based clustering approach of social media posts to extract clusters that provide insights into disaster-related content. A case study in the Ahr Valley region in Germany demonstrates the method’s effectiveness in providing actionable insights for disaster response and management. The approach offers a tool for the quick assessment of disaster-related information from social media, potentially aiding timely and informed decision-making.

STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models

Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific training data in the form of (passage, target structure) pairs to obtain reasonable performance. However, obtaining such data through human annotation is costly, leading to a pressing need for low-resource information extraction approaches that require minimal human labeling for real-world applications. Fine-tuning supervised models with synthesized training data would be a generalizable method, but the existing data generation methods either still rely on large-scale ground-truth data or cannot be applied to complicated IE tasks due to their poor performance. To address these challenges, we propose STAR, a data generation method that leverages Large Language Models (LLMs) to synthesize data instances given limited seed demonstrations, thereby boosting low-resource information extraction performance. Our approach involves generating target structures (Y) followed by generating passages (X), all accomplished with the aid of LLMs. We design fine-grained step-by-step instructions to obtain the initial data instances. We further reduce errors and improve data quality through self-reflection error identification and self-refinement with iterative revision. Our experiments show that the data generated by STAR significantly improve the performance of low-resource event extraction and relation extraction tasks, even surpassing the effectiveness of human-curated data. Human assessment of the data quality shows STAR-generated data exhibit higher passage quality and better align with the task definitions compared with the human-curated data.

A deep learning approach for robust traffic accident information extraction from online chinese news

AbstractRoad traffic accidents are the leading causes of injuries and fatalities. Understanding the traffic accident occurrence pattern and its contributing factors are prerequisites for effective traffic safety management. The paper proposes a deep learning approach for traffic accident recognition and information extraction from online Chinese news to extract and organize traffic accidents automatically. The approach consists of three modules, including automated news collection, news classification, and traffic accident information extraction. The automated news collection module crawls news from online sources, cleans and organizes it into a general news database with different categories of news. The news classification module robustly recognizes the traffic accident news from all types of news by fusing the sentence‐wise and context‐wise semantic news information. The accident information extraction module extracts the key attributes of traffic accidents (e.g. causes, times, locations) from news text using the SoftLexicon‐BiLSTM‐CRF method. The proposed approach is validated by comparing it with state‐of‐the‐art text mining methods using Chinese news data crawled online. The results show that the approach can achieve a high information extraction performance in terms of precision, recall, and F1‐score. It improves the performance of the best benchmark model (BiLSTM‐CRF) by 18.8% in precision and 12.08% in F1‐score. In addition, the potential value of the automatically extracted accident data is illustrated from online news in complementing traditional authority accident data to drive more effective traffic safety management in practice.

MSFANet: multi-scale fusion attention network for mangrove remote sensing lmage segmentation using pattern recognition

Mangroves are ecosystems that grow in the intertidal areas of coastal zones, playing crucial ecological roles and possessing unique economic and social values. They have garnered significant attention and research interest. Semantic segmentation of mangroves is a fundamental step for further investigations. However, mangrove remote sensing images often have large dimensions, with a substantial portion of the image containing mangrove features. Deep learning convolutional kernels may lead to inadequate receptive fields for accurate mangrove recognition. In mangrove remote sensing images, various challenges arise, including the presence of small and intricate details aside from the mangrove regions, which intensify the segmentation complexity. To address these issues, this paper primarily focuses on two key aspects: first, the exploration of methods to achieve a large receptive field, and second, the fusion of multi-scale information. To this end, we propose the Multi-Scale Fusion Attention Network (MSFANet), which incorporates a multi-scale network structure with a large receptive field for feature fusion. We emphasize preserving spatial information by integrating spatial data across different scales, employing separable convolutions to reduce computational complexity. Additionally, we introduce an Attention Fusion Module (AFM). This module helps mitigate the influence of irrelevant information and enhances segmentation quality. To retain more semantic information, this paper introduces a dual channel approach for information extraction through the deep structure of ResNet. We fuse features using the Feature Fusion Module (FFM) to combine both semantic and spatial information for the final output, further enhancing segmentation accuracy. In this study, a total of 230 images with dimensions of 768 pixels in width and height were selected for this experiment, with 184 images used for training and 46 images for validation. Experimental results demonstrate that our proposed method achieves excellent segmentation results on a small sample dataset of remote-sensing images, with significant practical value. This paper primarily focuses on three key aspects: the generation of mangrove datasets, the preprocessing of mangrove data, and the design and training of models. The primary contribution of this paper lies in the development of an effective approach for multi-scale information fusion and advanced feature preservation, providing a novel solution for mangrove remote sensing image segmentation tasks. The best Mean Intersection over Union (MIoU) achieved on the mangrove dataset is 86%, surpassing other existing models by a significant margin.

Estimation of Wheat Crop Production using Multispectral Information Fusion.

The present work estimates the area and the corresponding produce of wheat crop in the study area, which comprises Etah region of Uttar Pradesh, India. For this purpose, multispectral images of multiple sensors, viz., Sentinel-2, Landsat-8, and Landsat-9 during the preharvesting period, i.e., March for the years 2021 and 2022 are used. A multispectral information fusion approach has been proposed which involves image classification as well as vegetation index-based information extraction. For imposing the information fusion, appropriate image bands are identified with the help of separability analysis followed by land cover classification for wheat crop class extraction. Support Vector Machine (SVM), Artificial Neural Network (ANN) and Maximum Likelihood (ML) are used for classification whereas Normalized Difference Vegetation Index (NDVI) and Fractional Vegetation Cover (FVC) are used for index-based crop area extraction. The maximum accuracy of 98.34% is achieved for Sentinel-2 data using ANN whereas minimum accuracy of 80.21% is achieved for Landsat-9 using ML classifier. The estimated area for Sentinel-2 data for the year 2021 is 260540 hectares using ANN and 203240 hectares using ML which is near to the reference data, i.e., 238600 hectares. SVM also shows good performance and calculates least error in estimated crop area for the year 2022 on Sentinel-2 data. It calculates 8408490 tons of wheat for the same year. The proposed method utilizes a single image per year for extraction of information supported by the ground truth data which makes it a novel approach of information extraction for crop produce monitoring. This article is protected by copyright. All rights reserved.

Reliability Evaluation Based on the Colored Petri Net Converted from AADL Models for the Wheel Brake System of Aircraft

Traditional reliability analysis methods such as Reliability Block Diagram, Fault Tree Analysis, and Markov Analysis are all subjective methods whose results significantly depend on the analysts’ skills and experiences. A model-based reliability method is proposed for the wheel brake system by using the architectural analysis and design language (AADL). The wheel brake system is modeled based on the AADL, and the AADL Error Model Annex is applied to describe the fault propagation of the system. An information extraction approach is proposed for the AADL-based model, and rules for transforming AADL-based models to colored Petri nets are given according to the information extracted. The reliability analysis of the wheel brake system is conducted in terms of the Colored Petri Nets. Through Monte Carlo simulation and linear regression, it is inferred that the lifetime of the wheel brake system follows a Weibull distribution with shape parameter 1.303 and scale parameter 9.992 × 103, and the accuracy of the method has been verified. In this study, the reliability analysis results are generated via the system model automatically; they do not depend on the analysts’ experiences and skills, and ambiguity among different analysts can be avoided.

FVI-BD: Multiple File Extraction using Fusion Vector Investigation (FVI) in Big Data Hadoop Environment

— The Information Extraction (IE) approach extracts useful data from unstructured and semi-structured data. Big Data, with its rising volume of multidimensional unstructured data, provides new tools for IE. Traditional Information Extraction (IE) systems are incapable of appropriately handling this massive flood of unstructured data. The processing capability of current IE systems must be enhanced because to the amount and variety of Big Data. Existing IE techniques for data preparation, extraction, and transformation, as well as representations of massive amounts of multidimensional, unstructured data, must be evaluated in terms of their capabilities and limits. The proposed FVI-BD Framework for IOT device Information Extraction in Big Data. The unstructured data has cleaned and integration using POS tagging and similarity finding using LTA method. The features are extracted using TF and IDF. The Information extracted using NLP with WordNet. The classification has done with FVI algorithm. This research paper discovered that vast data analytics may be enhanced by extracting document feature terms with synonymous similarity and increasing IE accuracy.

Toward alert triage: scalable qualitative coding framework for analyzing alert notes from the Telehealth Intervention Program for Seniors (TIPS).

Combined with mobile monitoring devices, telehealth generates overwhelming data, which could cause clinician burnout and overlooking critical patient status. Developing novel and efficient ways to correctly triage such data will be critical to a successful telehealth adoption. We aim to develop an automated classification framework of existing nurses' notes for each alert that will serve as a training dataset for a future alert triage system for telehealth programs. We analyzed and developed a coding framework and a regular expression-based keyword match approach based on the information of 24 931 alert notes from a community-based telehealth program. We evaluated our automated alert triaging model for its scalability on a stratified sampling of 800 alert notes for precision and recall analysis. We found 22 717 out of 24 579 alert notes (92%) belonging to at least one of the 17 codes. The evaluation of the automated alert note analysis using the regular expression-based information extraction approach resulted in an average precision of 0.86 (SD = 0.13) and recall 0.90 (SD = 0.13). The high-performance results show the feasibility and the scalability potential of this approach in community-based, low-income older adult telehealth settings. The resulting coded alert notes can be combined with participants' health monitoring results to generate predictive models and to triage false alerts. The findings build steps toward developing an automated alert triaging model to improve the identification of alert types in remote health monitoring and telehealth systems.

Lane Information Extraction for High Definition Maps Using Crowdsourced Data

Lane information plays an important role in high-definition (HD) maps because it provides invaluable road information for autonomous vehicles. The most widely used lane extraction method for HD maps is based on mobile mapping systems, and it is prohibitively costly and time-consuming. In this study, we propose a novel approach for lane information extraction based on crowdsourcing vehicles equipped with monocular cameras and global navigation satellite system devices for recording road images and position data. First, we propose a lane mask propagation network to detect the lane markings in images, which are then projected from a perspective space into a three-dimensional space in accordance with the position data. Second, we propose a data management method to store lane information in the cloud data center. An improved density-based spatial clustering of applications with noise clustering algorithm and a gradual fitting algorithm are used to remove the outliers and improve the lane data accuracy. The proposed method is quantitatively evaluated against a real-world HD map produced by a mobile mapping vehicle. The experimental results show that more than 80% of the extracted lane markings meet the accuracy requirements of HD maps. In conclusion, our method can be used as a low-cost and efficient approach for updating the lane information in HD maps for autonomous vehicles.

Review of Natural Language Processing in Pharmacology.

Natural language processing (NLP) is an area of artificial intelligence that applies information technologies to process the human language, understand it to a certain degree, and use it in various applications. This area has rapidly developed in the past few years and now employs modern variants of deep neural networks to extract relevant patterns from large text corpora. The main objective of this work is to survey the recent use of NLP in the field of pharmacology. As our work shows, NLP is a highly relevant information extraction and processing approach for pharmacology. It has been used extensively, from intelligent searches through thousands of medical documents to finding traces of adversarial drug interactions in social media. We split our coverage into five categories to survey modern NLP: methodology, commonly addressed tasks, relevant textual data, knowledge bases, and useful programming libraries. We split each of the five categories into appropriate subcategories, describe their main properties and ideas, and summarize them in a tabular form. The resulting survey presents a comprehensive overview of the area, useful to practitioners and interested observers. SIGNIFICANCE STATEMENT: The main objective of this work is to survey the recent use of NLP in the field of pharmacology in order to provide a comprehensive overview of the current state in the area after the rapid developments that occurred in the past few years. The resulting survey will be useful to practitioners and interested observers in the domain.

A Canonical Context-Preserving Representation for Open IE: Extracting Semantically Typed Relational Tuples from Complex Sentences

Modern systems that deal with inference in texts need automatized methods to extract meaning representations (MRs) from texts at scale. Open Information Extraction (IE) is a prominent way of extracting all potential relations from a given text in a comprehensive manner. Previous work in this area has mainly focused on the extraction of isolated relational tuples. Ignoring the cohesive nature of texts where important contextual information is spread across clauses or sentences, state-of-the-art Open IE approaches are thus prone to generating a loose arrangement of tuples that lack the expressiveness needed to infer the true meaning of complex assertions.To overcome this limitation, we present a method that allows existing Open IE systems to enrich their output with additional meta information. By leveraging the semantic hierarchy of minimal propositions generated by the discourse-aware Text Simplification (TS) approach presented in Niklaus et al. (2019), we propose a mechanism to extract semantically typed relational tuples from complex source sentences. Based on this novel type of output, we introduce a lightweight semantic representation for Open IE in the form of normalized and context-preserving relational tuples. It extends the shallow semantic representation of state-of-the-art approaches in the form of predicate-argument structures by capturing intra-sentential rhetorical structures and hierarchical relationships between the relational tuples. In that way, the semantic context of the extracted tuples is preserved, resulting in more informative and coherent predicate-argument structures which are easier to interpret.In addition, in a comparative analysis, we show that the semantic hierarchy of minimal propositions benefits Open IE approaches in a second dimension: the canonical structure of the simplified sentences is easier to process and analyze, and thus facilitates the extraction of relational tuples, resulting in an improved precision (up to 32%) and recall (up to 30%) of the extracted relations on a large benchmark corpus.

Dynamic Editing Distance-based Extracting Relevant Information Approach from Social Networks

Online social networks, such as Facebook, Twitter, LinkedIn, etc., have grown exponentially in recent times with a large amount of information. These social networks have huge volumes of data especially in structured, textual, and unstructured forms which have often led to cyber-crimes like cyber terrorism, cyber bullying, etc., and extracting information from these data has now become a serious challenge in order to ensure the data safety. In this work, we propose a new, supervised approach for Information Extraction (IE) from Web resources based on remote dynamic editing, called EIDED. Our approach is part of the family of IE approaches based on masks extraction and is articulated around three algorithms: (i) a labeling algorithm, (ii) a learning and inference algorithm, and (iii) an extended edit distance algorithm. Our proposed approach is able to work even in the presence of anomalies in the tuples such as missing attributes, multivalued attributes, permutation of attributes, and in the structure of web pages. The experimental study, which we conducted, on a standard database of web pages, shows the performance of our EIDED approach compared to approaches based on the classic edit distance, and this with respect to the standard metrics recall coefficient, precision, and F1-measure.

Neural Semantic Parsing of Building Regulations for Compliance Checking

Computerising building regulations to allow reasoning is one of the main challenges in automated compliance checking in the built environment. While there has been a long history of translating regulations manually, in recent years, natural language processing (NLP) has been used to support or automate this task. While rule- and ontology-based information extraction and transformation approaches have achieved accurate translations for narrow domains and specific regulation types, machine learning (ML) promises increased scalability and adaptability to new regulation styles. Since ML usually requires many annotated examples as training data, we take advantage of the long history of building code computerisation and use a corpus of manually translated regulations to train a transformer-based encoder-decoder model. Given a relatively small corpus, the model learns to predict the logical structure and extracts entities and relations reasonably well. While the translation quality is not adequate to fully automate the process, the model shows the potential to serve as an auto-completion system and to identify manually translated regulations that need to be reviewed.