Information Extraction Process Research Articles

Information extraction for different layouts of invoice images

ABSTRACT In the organization, they purchased goods or services from different suppliers and used invoice documents to confirm the payment. The invoice documents contained information that can be used for a business decision but, the process of information extraction required many resources to collect the data. The traditional way used template matching-based methods. This process identifies the parts on an image that match a predefined template and requires new manual annotation when processing the new image layout. Therefore, developing a system for robustly extracting entities from different layouts of invoices is necessary. Existing research applied deep learning and Name Entity Recognition (NER) for information extraction but, extracting invoice information was widely done in English and Chinese languages. In this study, we constructed a deep learning model using BiLSTM-CRF (Bidirectional Long Short-Term Memory-Conditional Random Fields) with word and character embedding for information extraction from different layouts of Thai invoice images. The model was evaluated by Semantic Evaluation at a full named-entity level. Our experimental results showed that this method can achieve a precision of 0.9557, recall of 0.9486, and F1-score of 0.9521 for the partial match; precision of 0.9329, recall of 0.9259, and F1-score of 0.9294 for the exact match and the result of the F1-score was significantly influenced by the quality of images and text result from Optical Character Recognition (OCR). Abbreviations: BERT: bidirectional encoder representations from transformers; BiLSTM: bidirectional long short-term memory; COR: correct; CRF: conditional random fields; CV: computer vision; ELMO: embeddings from language model; INC: incorrect; MIS: missing; MSE: mean squared error; MUC: message understanding conference; NER: named entity recognition; NLP: natural language processing; OCR: optical character recognition; PAR: partial; SemEval: semantic evaluation; SPU: spurius

Large-Scale System for Social Media Data Warehousing

Social media data become an integral part in the business data and should be integrated into the decisional process for better decision making based on information which reflects better the true situation of business in any field. However, social media data are unstructured and generated in very high frequency which exceeds the capacity of the data warehouse. In this work, we propose to extend the data warehousing process with a staging area which heart is a large scale system implementing an information extraction process using Storm and Hadoop frameworks to better manage their volume and frequency. Concerning structured information extraction, mainly events, we combine a set of techniques from NLP, linguistic rules and machine learning to succeed the task. Finally, we propose the adequate data warehouse conceptual model for events modeling and integration with enterprise data warehouse using an intermediate table called Bridge table. For application and experiments, we focus on drug abuse events extraction from Twitter data and their modeling into the Event Data Warehouse.

Reduced Reference Quality Assessment for Image Retargeting by Earth Mover’s Distance

A reduced reference quality assessment algorithm for image retargeting by earth mover’s distance is proposed in this paper. In the reference image, all the feature points are extracted using scale invariant feature transform. Let the histograms of image patch around each feature point be local information, and the histograms of saliency feature as global information. Those feature information is extracted at the sender side and transmitted to the receiver side. After that, the same feature information extraction process is performed for the retargeted image at the receiver side. Finally, all feature information of the reference and retargeted images is used collectively to compute the quality of the retargeted image. An overall quality score is calculated from the local and global similarity measure using earth mover’s distance between reference and retargeted images. The key step in our algorithm is to provide an earth mover’s distance metric in a manner that indicates how the local and global information in the reference image is preserved in corresponding retargeted image. Experimental results show that the proposed algorithm can improve the image quality scores on four common criteria in the retargeted image quality assessment community.

Low-Quality Error Detection for Noisy Knowledge Graphs

The automatic construction of knowledge graphs (KGs) from multiple data sources has received increasing attention. The automatic construction process inevitably brings considerable noise, especially in the construction of KGs from unstructured text. The noise in a KG can be divided into two categories: factual noise and low-quality noise. Factual noise refers to plausible triples that meet the requirements of ontology constraints. For example, the plausible triple <New_York, IsCapitalOf, America> satisfies the constraints that the head entity “New_York” is a city and the tail entity “America” belongs to a country. Low-quality noise denotes the obvious errors commonly created in information extraction processes. This study focuses on entity type errors. Most existing approaches concentrate on refining an existing KG, assuming that the type information of most entities or the ontology information in the KG is known in advance. However, such methods may not be suitable at the start of a KG's construction. Therefore, the authors propose an effective framework to eliminate entity type errors. The experimental results demonstrate the effectiveness of the proposed method.

A deep neural network-based method for deep information extraction using transfer learning strategies to support automated compliance checking

Existing automated compliance checking (ACC) systems require the extraction of requirements from regulatory documents into computer-processable representations. These information extraction (IE) processes are either fully manual, semi-automated, or automated. Semi-automated and manual approaches typically use manual annotations or predefined IE rules, which lack sufficient flexibility and scalability; the annotations and rules typically need adaptation if the characteristics of the regulatory document change. There is, thus, a need for a fully automated IE approach that can achieve high and consistent performance across different types of regulatory documents for supporting ACC. To address this need, this paper proposes a deep neural network-based method for deep IE – extracting semantic and syntactic information elements – from regulatory documents in the architectural, engineering, and construction (AEC) domain. The proposed method was evaluated in extracting information from multiple regulatory documents in the AEC domain. It achieved average precision and recall of 93.1% and 92.9%, respectively.

Exploring the Adaptation of Recurrent Neural Network Approaches for Extracting Drug–Drug Interactions from Biomedical Text

Information extraction (IE) is the process of automatically identifying structured information from unstructured or partially structured text. IE processes can involve several activities, such as named entity recognition, event extraction, relationship discovery, and document classification, with the overall goal of translating text into a more structured form. Information on the changes in the effect of a drug, when taken in combination with a second drug, is known as drug–drug interaction (DDI). DDIs can delay, decrease, or enhance absorption of drugs and thus decrease or increase their efficacy or cause adverse effects. Recent research trends have shown several adaptation of recurrent neural networks (RNNs) from text. In this study, we highlight significant challenges of using RNNs in biomedical text processing and propose automatic extraction of DDIs aiming at overcoming some challenges. Our results show that the system is competitive against other systems for the task of extracting DDIs.

Deep learning-based protocols to enhance infrared imaging systems

Infrared (IR) spectroscopic imaging provides both morphologic and chemical detail; however, obtaining this extensive spectral-spatial information requires the ability to rapidly record high-quality data. Discrete frequency infrared (DFIR) imaging using a point scanning microscope strikes a balance between data quality and acquisition speed that, in principle, can further be aided by computational methods. Here, we report a deep learning-based framework to complement the process of data acquisition and information extraction. First, we introduce a convolutional neural network (CNN) to leverage both spatial and spectral information for segmenting data into informative sub-classes, which we call the IR-SEG network. We show that this framework increases accuracy by using approximately half of the features used in the typical pixel-wise classification of IR data. Second, we present a generative adversarial network (GAN)-based approach to reconstruct full data sets with low loss in the information from incomplete spatial and spectral data recording. Termed IR-REC, this approach is shown to speed up data acquisition by up to 20-fold for typical biomedical samples. In addition to enhancing the speed and quality of data, we also propose a method to utilize complementary morphologic detail to estimate the spatial details of a single band IR image beyond the diffraction limit. Finally, we discuss potential pitfalls and new opportunities that can be addressed by developing these methods further. Together, these deep learning techniques provide new capabilities for IR imaging to extract better quality information faster.

Task-based support in search engines

Darío Garigliotti is a postdoctoral researcher at Aalborg University, Denmark, where he works in collaboration with Prof. Katja Hose and Assoc. Prof. Johannes Bjerva, in the areas of information extraction, information retrieval and natural language processing. He completed his doctoral degree in Computer Science at University of Stavanger, Norway, under the supervision of Prof. Krisztian Balog. The website at https://dariogarigliotti.github.io/ contains more information about Garigliotti's work. The research conducted by Garigliotti focused on utilizing and extending methods and techniques from semantic search within an information access paradigm that aims to support users in achieving their tasks. More specifically, to enhance search engines with functionalities for recognizing the underlying tasks in searches and providing support for task completion. The work presented in this thesis is organized in three grand themes: entity type information for entity retrieval, entity-oriented search intents, and task-based search. Alongside the theoretical and empirical contributions, a number of resource contributions were developed, including several corpora and test collections, and a knowledge base of entity-oriented search intents.

Survey of Process of Data Discovery and Environmental Decision Support Systems

The process of data discovery is an approach to extracting knowledge, valid, and usable information from large amounts of data, using automatic or semi-automatic methods. This article is an inventory of the different information extraction processes encountered in the literature for different fields of application and for the development of environmental informatics. Following an analysis between the different models, we can summarize the existing models with a proposal for a process that exploits the strengths of the different processes.

CAFE: Knowledge graph completion using neighborhood-aware features

Knowledge Graphs (KGs) currently contain a vast amount of structured information in the form of entities and relations. Because KGs are often constructed automatically by means of information extraction processes, they may miss information that was either not present in the original source or not successfully extracted. As a result, KGs might lack useful and valuable information. Current approaches that aim to complete missing information in KGs have two main drawbacks. First, some have a dependence on embedded representations, which impose a very expensive preprocessing step and need to be recomputed again as the KG grows. Second, others are based on long random paths that may not cover all relevant information, whereas exhaustively analyzing all possible paths between entities is very time-consuming. In this paper, we present an approach to complete KGs based on evaluating candidate triples using a set of neighborhood-based features. Our approach exploits the highly connected nature of KGs by analyzing the entities and relations surrounding any given pair of entities, while avoiding full recomputations as new entities are added. Our results indicate that our proposal is able to identify correct triples with a higher effectiveness than other state-of-the-art approaches, achieving higher average F1 scores in all tested datasets. Therefore, we conclude that the information present in the vicinities of the two entities within a candidate triple can be leveraged to determine whether that triple is missing from the KG or not.

Job Standard Parameters from Online Job Vacancy

The internet has provided an efficient and economical way to provide job vacancy information to applicants in a way that is far more dynamic and consistent than happened in the past. This is directly proportional to the number of companies exploiting online technology (job portals, company websites, etc.) to make job advertisements reach a growing audience. To further optimize the selection process concerning processing time and accuracy, researchers have begun developing a sophisticated search engine to automatically sort resumes based on job offer requirements. Overcoming this problem requires the Information Extraction (IE) process. Research on IE regarding vacancies actually already exists and has been applied. Research on IE regarding vacancies actually already exists and has been applied In addition, we want to develop previous research involving all job vacancies websites to a wider extent. We realize that this limitation makes the extraction process difficult. we try to define job problems more easily, such as identifying various JSPs on job vacancy websites in Indonesia as a first step in the extraction process. Our findings in the survey of 14 job vacancy websites are 26 job standard parameters including structure collection and extraction methods. This study provides a detailed description of each component of information extraction on the job vacancy website in Indonesia. Starting from identifying the type of Structured Extraction to the output of extraction. This study also developed JSP from previous research.

WITHDRAWN: A Customized Profile-Aware news system for filtering and summarizing

A significant amount of news material consists of information on the Internet. In Web information, a lot of interest has been devoted to web news tips, filtering, and review, focused at identifying interesting information and analyzing informative user information. We implement our research into the development of the Information Extraction and Summary Process. An integrated part of learning triggers a user interest model and suggests user specific news. An expert system of key words is retained and offers an actual overview to represent the specific matter of web information and the desires of the reader. Not interested and unwanted news content that is unrelated to the news platform is filtered out. Key terms that retrieve the main description of the news Through linguistic sequences, information is retrieved to represent semantic connections between words and Providing refined data, such as a description Versions of the source text and highlights key words in the text that are significant.

Firefly Optimization Algorithm Based Web Scraping for Web Citation Extraction

Web citation analysis is primarily used to examine the impact of an author, an article or a publication by counting the amount of intervals that has been cited by other authors. The significant goal of web citation analysis is helping the researchers to find their related papers for their further analysis. The references of the paper must be cited by the author, which is used to recognize the link among the previous relevant research. The citation provides the valuable information that directs the researchers to gain knowledge about the current trends and future developments and obtain new ideas in their respective fields. The citation’s information are incorporate in the database called web citation database such as Google Scholar, Web of Science, Scopus and so on. From the web citation database, extracting the user required information is very complex task. Most of the open source tools are available online but manual process is needed to select the user-required information from the web page. For instance if the user need author name and publisher from the web citation database, they required to choose the exact information tags manually in existing tools which consumes more time. To overcome this difficulty we proposed an algorithm Firefly Optimization Algorithm based Web Scraping for web content extraction from web citation database. The primary purpose of this research is to extract author information extraction process extracts citation information published by an author, journal name, publisher, year and citation using web citation analysis. The user’s query input will be the keyword for example big data, artificial intelligence, etc. The web citation information from multiple web pages using Web crawling and web scraping techniques are applied for web citation information based on the user query and Particle Swarm Optimization, Hidden Markov Model are applied for finding the best solution from all the feasible solutions. Experiments illustrate the proposed FOAWS algorithm outperforms well comparing to other two algorithms.

The Effect of Brill Tagger on The Classification Results of Sentiment Analysis Using Multinomial Naïve Bayes Algorithm

Twitter is a good indicator for influence in research, the problem thatarises in research in the field of sentiment analysis is the large numberof factors such as the use of informal or colloquial language and otherfactors that can affect the results of sentiment classification. Toimprove the results of sentiment classification, an informationextraction process can be carried out. One part of the informationextraction feature is a part of speech tagging, which is the giving ofword classes automatically. The results of part of speech tagging areused for weighting words based on part of speech. This studyexamines the effect of Part of Speech Tagging with the method BrillTagger in sentiment analysis using the Naive Bayes Multinomialalgorithm. Testing were carried out on 500 twitter tweet texts andobtained the results of the sentiment classification with implementingpart of speech tagging precision by 73,2%, recall by 63,2%, f-measureby 67,6%, accuracy by 60,7% and without implementing part ofspeech tagging precision by 65,2%, recall by 60,6%, f-measure by62,4% accuracy by 53,3%. From the results of the accuracy obtained,it shows that the application of part of speech tagging in sentimentanalysis using the Multinomial Naïve Bayes algorithm has an effectwith an increase in classification performance.

Multi-Feature Sample Database for Enhancing Deep Learning Tasks in Operational Humanitarian Applications

Amongst the many benefits of remote sensing techniques in disaster- or conflict-related applications, timeliness and objectivity may be the most critical assets. Recently, increasing sensor quality and data availability have shifted the attention more towards the information extraction process itself. With promising results obtained by deep learning (DL), the notion arises that DL is not agnostic to input errors or biases introduced, in particular in sample-scarce situations. The present work seeks to understand the influence of different sample quality aspects propagating through network layers in automated image analysis. In this paper, we broadly discuss the conceptualisation of such a sample database in an early stage of realisation: (1) inherited properties (quality parameters of the underlying image such as cloud cover, seasonality, etc.); (2) individual (i.e., per-sample) properties, including a. lineage and provenance, b. geometric properties (size, orientation, shape), c. spectral features (standardized colour code); (3) context-related properties (arrangement Several hundred samples collected from different camp settings were hand-selected and annotated with computed features in an initial stage. The supervised annotation routine is automated so that thousands of existing samples can be labelled with this extended feature set. This should better condition the subsequent DL tasks in a hybrid AI approach.

A Systematic Review Web Content Mining Tools and its Applications

In recent years, the emergence of WWW (World Wide Web) led to the accumulation of huge amount of information and data. Hence the web is found to consist of unstructured and structured information that impacts the day to day life of the society. Because of such availability of huge information, utilization of the required information becomes more challenging. This paper provided a comprehensive survey on the current situation and recent trends on web content mining (WCM) and its applications thereby contributing to the enhancement of the upcoming research in WCM. The paper focused mainly on the mining and retrieval techniques, various WCM approaches, challenges and process of information retrieval and information extraction. The paper describes the four major tasks of web content mining that is information retrieval, information extraction, generalization and validation in detail. WCM concentrates on orchestrating, sorting, classifying, collecting, congregating of web data and provide the improved data which can be easily accessed by the users. Web content mining tools were needed to scan text, images and HTML documents and provide results to the search engine. It guides the search engine to provide better productive results for every search based on their importance. The paper also analysed different web content mining tools for the extraction of relevant information from the corresponding web page.

Optical Character Recognition Engines Performance Comparison in Information Extraction

Named Entity Recognition (NER) is often used to acquire important information from text documents as a part of the Information Extraction (IE) process. However, the text documents quality affects the accuracy of the data obtained, especially for text documents acquired involving the Optical Character Recognition (OCR) process, which never reached 100% accuracy. This research tried to examine which OCR engine with the highest performance for IE using NER by comparing three OCR engines (Foxit, PDF2GO, Tesseract) over 8,562 government human resources documents within six document categories, two document structures, and four measurements. Several essential entities such as name, employee ID, document number, document publishing date, employee rank, and family member's name were trying to be extracted automatically from the documents. NER processes were done using Python programming language, and the preprocessing tasks were done separately for Foxit, PDF2GO, and Tesseract. In summary, each OCR engine has its drawbacks and benefit, such as Tesseract has better NER extraction and conversion time with better accuracy but lack in the number of entities acquired.

Construction and Application of Knowledge Graph for Quality and Safety Supervision of Transportation Engineering

Knowledge graph technology play a more and more important role in various fields of industry and academia. This paper firstly introduces the general framework of the knowledge graph construction, which includes three stages: information extraction, knowledge fusion and knowledge processing. In order to improve the efficiency of quality and safety supervision of transportation engineering construction, this paper constructs a knowledge graph by acquiring multi-sources heterogeneous data from supervision of transportation engineering quality and safety. It employs a bottom-up construction strategy and some natural language processing methods to solve the problems of the knowledge extraction for transportation engineering construction. We use the entity relation extraction method to extract the entity triples from the multi-sources heterogeneous data, and then employ knowledge inference to complete the edges in the constructed knowledge graph, finally perform quality evaluation to add the valid triples to the knowledge graph for updating. Subgraph matching technology is also exploited to retrieve the constructed knowledge graph for efficiently acquiring the useful knowledge about the quality and safety of transportation engineering projects. The results show that the constructed knowledge graph provides a practical and valuable tool for the quality and safety supervision of transportation engineering construction.

Classification of Privacy Preserving Data Mining Algorithms: A Review

Nowadays, data from various sources are gathered and stored in databases. The collection of the data does not give a significant impact unless the database owner conducts certain data analysis such as using data mining techniques to the databases. Presently, the development of data mining techniques and algorithms provides significant benefits for the information extraction process in terms of the quality, accuracy, and precision results. Realizing the fact that performing data mining tasks using some available data mining algorithms may disclose sensitive information of data subject in the databases, an action to protect privacy should be taken into account by the data owner. Therefore, privacy preserving data mining (PPDM) is becoming an emerging field of study in the data mining research group. The main purpose of PPDM is to investigate the side effects of data mining methods that originate from the penetration into the privacy of individuals and organizations. In addition, it guarantees that the data miners cannot reveal any personal sensitive information contained in a database, while at the same time data utility of a sanitized database does not significantly differ from that of the original one. In this paper, we present a wide view of current PPDM techniques by classifying them based on their taxonomy techniques to differentiate the characteristics of each approach. The review of the PPDM methods is described comprehensively to provide a profound understanding of the methods along with advantages, challenges, and future development for researchers and practitioners.

Wind Turbine Data Analysis and LSTM-Based Prediction in SCADA System

The number of wind farms is increasing every year because many countries are turning their attention to renewable energy sources. Wind turbines are considered one of the best alternatives to produce clean energy. Most of the wind farms installed supervisory control and data acquisition (SCADA) system in their turbines to monitor wind turbines and logged the information as time-series data. It demands a powerful information extraction process for analysis and prediction. In this research, we present a data analysis framework to visualize the collected data from the SCADA system and recurrent neural network-based variant long short-term memory (LSTM) based prediction. The data analysis is presented in cartesian, polar, and cylindrical coordinates to understand the wind and energy generation relationship. The four features: wind speed, direction, generated active power, and theoretical power are predicted and compared with state-of-the-art methods. The obtained results confirm the applicability of our model in real-life scenarios that can assist the management team to manage the generated energy of wind turbines.