Search

Generating fluent, coherent, and informative text from structured data is called table-to-text generation. Copying words from the table is a common method to solve the “out-of-vocabulary” problem, but it’s difficult to achieve accurate copying. In order to overcome this problem, we invent an auto-regressive framework based on the transformer that combines a copying mechanism and language modeling to generate target texts. Firstly, to make the model better learn the semantic relevance between table and text, we apply a word transformation method, which incorporates the field and position information into the target text to acquire the position of where to copy. Then we propose two auxiliary learning objectives, namely table-text constraint loss and copy loss. Table-text constraint loss is used to effectively model table inputs, whereas copy loss is exploited to precisely copy word fragments from a table. Furthermore, we improve the text search strategy to reduce the probability of generating incoherent and repetitive sentences. The model is verified by experiments on two datasets and better results are obtained than the baseline model. On WIKIBIO, the result is improved from 45.47 to 46.87 on BLEU and from 41.54 to 42.28 on ROUGE. On ROTOWIRE, the result is increased by 4.29% on CO metric, and 1.93 points higher on BLEU.

An efficient full-text search is achieved by indexing the raw data with an additional 20 to 30 percent storagecost. In the context of Big Data, this additional storage space is huge and introduces challenges to entertainfull-text search queries with good performance. It also incurs overhead to store, manage, and update the largesize index. In this paper, we propose and evaluate a method to minimize the index size to offer full-text searchover Big Data using an automatic extractive-based text summarization method. To evaluate the effectivenessof the proposed approach, we used two real-world datasets. We indexed actual and summarized datasets usingApache Lucene and studied average simple overlapping, Spearman’s rho correlation, and average rankingscore measures of search results obtained using different search queries. Our experimental evaluation showsthat automatic text summarization is an effective method to reduce the index size significantly. We obtained amaximum of 82% reduction in index size with 42% higher relevance of the search results using the proposedsolution to minimize the full-text index size.

Verifiable pattern matching enables users to obtain authenticated query results over outsourced data on an untrusted remote server. It is a fundamental problem in many security-critical big data applications, including big database search, human genome data search, text search, etc., especially when these applications are outsourced to third-party clouds. However, the state-of-the-art schemes do not yet support efficient data updates. In this work, we propose the first dynamic verifiable pattern matching scheme to support efficient data updates. The proposed scheme is built on two ideas: one is to embed unique randomness to decouple the character and its index in the outsourced data, enabling efficient data updates; the other is to reduce the verifiable pattern matching problem to a discrete set membership testing problem, which relies on the decoupling introduced in the first idea. Based on these two ideas, the proposed scheme first employs the suffix array index structure to search pattern matching queries. The scheme then authenticates the outsourced text using a newly designed authenticated data structure based on the RSA accumulator, which guarantees the verifiability of pattern matching query results. Data update is naturally supported using the RSA accumulator working on discrete sets. Based on the proposed design, we have prototyped a proof-of-concept for the proposed scheme and have conducted an extensive experimental evaluation. In addition to supporting efficient data update, our experimental results show that the proposed scheme incurs reduced verification cost in comparison with the baseline state-of-the-art scheme.

Multi-keyword query is widely supported in text search engines. However, an analogue in image retrieval systems, multi-object query, is rarely studied. Meanwhile, traditional object-based image retrieval methods often involve multiple steps separately. In this work, we propose a weakly-supervised Deep Multiple Instance Hashing (DMIH) approach for multi-object image retrieval. Our DMIH approach, which leverages a popular CNN model to build the end-to-end relation between a raw image and the binary hash codes of its multiple objects, can support multi-object queries effectively and integrate object detection with hashing learning seamlessly. We treat object detection as a binary multiple instance learning (MIL) problem and such instances are automatically extracted from multi-scale convolutional feature maps. We also design a conditional random field (CRF) module to capture both the semantic and spatial relations among different class labels. For hashing training, we sample image pairs to learn their semantic relationships in terms of hash codes of the most probable proposals for owned labels as guided by object predictors. The two objectives benefit each other in a multi-task learning scheme. Finally, a two-level inverted index method is proposed to further speed up the retrieval of multi-object queries. Our DMIH approach outperforms state-of-the-arts on public benchmarks for object-based image retrieval and achieves promising results for multi-object queries.

Natural language processing (NLP) is a field of computer science concerned with automated text and language analysis. In recent years, following a series of breakthroughs in deep and machine learning, NLP methods have shown overwhelming progress. Here, we review the success, promise and pitfalls of applying NLP algorithms to the study of proteins. Proteins, which can be represented as strings of amino-acid letters, are a natural fit to many NLP methods. We explore the conceptual similarities and differences between proteins and language, and review a range of protein-related tasks amenable to machine learning. We present methods for encoding the information of proteins as text and analyzing it with NLP methods, reviewing classic concepts such as bag-of-words, k-mers/n-grams and text search, as well as modern techniques such as word embedding, contextualized embedding, deep learning and neural language models. In particular, we focus on recent innovations such as masked language modeling, self-supervised learning and attention-based models. Finally, we discuss trends and challenges in the intersection of NLP and protein research.

The users helped by the search engine for online transactions in e-commerce; nonetheless, there is still a lack of search interest from the user and online shopping intentions. To boost the user's search for product recommendations, use a search engine for the quest but not for purchasing purposes. Existing frameworks have some significant problems in the recommendation technology, such as new product problems, fewer evaluation problems, a vast amount of data, etc. Many e-commerce applications lack a better search experience like an Exploratory search system. This research work aims to create a conceptual model for recommendation systems using exploratory search, to study the behavior of users and the efficacy of exploratory search in terms of the quality of the search results produced. Several machine learning algorithms are used in this research to classify e-commerce products and evaluate the performance of these algorithms. The full-text search mechanism is used to implement an exploratory search system. The exploratory search system is evaluated by three criteria called to look up, learn and investigate. After the experiments and evaluation, it is observed that AdaBoost over decision tree performs better than the other classification algorithms implemented. The exploratory search system satisfies the three requirements that are lookup learn and investigate during the search process. Contributions to this work are to build a conceptual model for the recommendation system through the dataset of user events and finding the implementation of an exploratory search mechanism in an e-commerce application.

Semantic network model for representing data and knowledge was analysed. Selection of this model for working with text information was justified. The objective of automatic semantic network generation based on an arbitrary Russian-language text was formulated. Initial data, conditions and constraints necessary for network generation algorithm are listed. As a result of the part-of-speech analysis for each word and word order in a sentence, semantic relations between words are determined. The Lexeme dictionary was created to determine the part of speech of words in sentences. A set of question types used in the semantic network was selected. The number of relations in the network is regulated due to the possibility to use only necessary relation types when resolving a specific task. With that, the relations in semantic network can have very different types, which makes it a universal model for representing data and knowledge. The algorithm was developed which allows one to get answers for the questions asked. The semantic network model was generated automatically for the sentences considered. In the proposed algorithm the semantic network is interpreted as unoriented graph on which breadth-first search algorithm is used to find an answer. The proposed algorithms were implemented in a software tool which automatically generates the semantic network for an arbitrary text. The created software tool allows asking questions and getting answers to them based on the information which is stored in the semantic network. The experiments have shown that the generated semantic network gives correct answers to the questions posed. The network is modified by adding and removing information in it. There is a possibility to choose complexity of network structure depending on a specific task being resolved. The proposed approach for building and working with the semantic network allows one to process texts in various languages, to use it in information systems with natural-language interface, and to resolve such tasks as text classification and text search.

Recent technological developments have increased the use of machine learning to solve many problems, including many in information retrieval (IR). Deployment of machine-learning techniques is widespread in text search, notability web search engines (Dai et al., 2011). Multimedia information retrieval as a problem however still represents a significant challenge to machine learning as a technological solution, but some problems in IR can still be addressed by using appropriate AI techniques. In this paper we review the technological developments, and provide a perspective on the use of machine-learning techniques in conjunction with knowledge organisation techniques to address multimedia IR needs. We take the perspective from the MacFarlane (2016) position paper, that there are some problems in multimedia IR that AI and machine learning cannot currently solve. The semantic gap in multimedia IR (Enser, 2008) remains a significant problem in the field, and solutions to them are many years off. However, there are occasions where the new technological developments allow the use of knowledge organisation and machine learning in multimedia search systems and services. Specifically we argue that the improvement of detection of some classes of low level features in images (Karpathy and Li, 2015), music (Byrd and Crawford, 2002) and video (Hu et al., 2011) can be used in conjunction with knowledge organisation to tag or label multimedia content for better retrieval performance. We advocate the use of supervised learning techniques. We provide an overview of the use of knowledge organisation schemes in machine learning, and make recommendations to information professionals on the use of this technology with knowledge organisation techniques to solve multimedia IR problems.

SOMHunter represents a modern light-weight framework for known-item search in datasets of visual data like images or videos. The framework combines an effective W2VV++ text-to-image search approach, a traditional Bayesian like model for maintenance of relevance scores influenced by positive examples, and several types of exploration and exploitation displays. With this initial setting in 2020, already the first prototype of the system turned out to be highly competitive in comparison with other state-of-the-art systems at Video Browser Showdown and Lifelog Search Challenge competitions. In this paper, we present a new version of the system further extending the list of visual data search capabilities. The new version combines localized text queries with collage queries tested at VBS 2021 in two separate systems by our team. Furthermore, the new version of SOMHunter will integrate also the new CLIP text search model recently released by OpenAI. We believe that all the extensions will improve chances to effectively initialize the search that can continue with already supported browsing capabilities.

The data management system (DMS) developed in SNERDI is a central platform for data collection, storage, control, configuration, display, and application of all engineering data, serving for project design and management. The four-layer architecture of the DMS is proposed, and considering the specialty of nuclear power design data, key mechanisms on data modeling and storage, data collection, full text search, data visualization, and plant information model configuration are studied and solutions are presented. Specifically, the data is stored by a “name-value separation” method in which metadata and value is separately modeled and stored. Design data is collected through interfaces which acquire data either by standard template or by data extraction from engineering documents and 3D models. For full text search, all the documents are converted into plain text files, and the DMS database is “content-restored” into JSON-formatted files. Data visualization solves the problem of data display friendly and graphically, as well as 3D models navigation. The plant information model is configured by a three-step cascade style.

In this paper there are results of the bachelor and master theses citing analysis. These students graduated from the Higher mathematics chair of the Russian Technological University in the summer of 2018. In this comparative analysis the dependencies of thesis loan percent on parameters of students, statistical values of their theses are explored. This research is actual because of the progress and development of new informational technologies used in the educational system. Popularity of the text loan detection systems increases. Automatic plagiarism detection systems are intended to make educational process better, the text drawing search easier, to support the copyright laws and academical honesty. The percentage is given by two main Russian plagiarism detection systems: Antiplagiat and Rucontext. Connections between thesis parameters are explored. Advantages of each text loan detection systems are described. In this research there are the results of the pedagogical experiment aimed to analyze statistically the dependencies of the bachelor’s and master’s theses loan percentage which have been got from Antiplagiat and Rucontext systems on the author’s parameters, statistical values describing thesis text. The comparison between statistical results of these systems have been made. The conclusions about their advantages have been presented in the paper. In order to make the comparison methods of the mathematical statistics have been used. Numerical experiment has been provided by means of the packages of the R statistical language. The difference between text loan percentages in the Antiplagiat and Rucontext systems has been analyzed. It has been shown that it grows when length of the text becomes larger. The dependencies of the text loan percentage on the available parameters of the thesis author and text parameters have been presented. The dependencies types are the same for the both systems. Scale of the coefficients in the statistical dependencies is also the same. The difference is in the very set of the parameters: the Rucontext percentage is better described statistically with the sex of the author, the Antiplagiat percentage is described with the type of the higher education (bachelor’s or master’s thesis). Also the dependency of the text loan percentage on the length of the thesis text differs: the Antiplagiat percentage is better described statistically with the number of words but the Rucontext percentage is described with the number of characters. It seems that these differences can be explained with different text search and analyze algorithms. The dependencies between the Rucontext percentage and the Antiplagiat text loan percentage is presented.

In today’s world, shopping has an important place in people’s lives in order to meet their basic needs, and people often spend a lot of time and energy to buy high-quality products at a cheap price. In addition, the cheapest product available on any day and hour may be at a different price one day later. The same product may be priced very differently in one market than in another. Despite the inconsistency and dynamic changes in all these prices, it was planned to collect the data with the crowdsourcing method in order to be able to search for the best price instantly with instant queries. In this developed product, in order to keep up with the dynamism of the data, a software was developed that will enable the data of products to be entered via smart phones with plain text-messages, from anywhere and by anyone, and the data was collected in a document-based NoSQL database. Since the data are unstructured messages, word-based indexing and distributed search architectures Lucene and Elasticsearch, which provide full-text search, were used. Since accessibility is important as well as the most affordable price, various services were integrated into the system with the Google Map API integration.

Natural Language Processing (NLP) field experienced considerable improvement in the year 2018. With the help of the transfer learning approach BERT (Bidirectional Encoder Representations) introduced by Google and approaches following it, state-of-the-art results were achieved in many NLP tasks. It became easier to research in this direction for Turkish with the help of published Turkish pre-trained BERT models in February, 2020. A new opportunity has arisen on research and development of contextual embeddings-based document retrieval instead of keyword-based for Turkish. This work introduces a BERT-contextual-vector-based Turkish text search tool. Sample queries and responses are presented to demonstrate the benefits it brings.

Information extraction from narrative clinical notes is useful for patient care, as well as for secondary use of medical data, for research or clinical purposes. Many studies focused on information extraction from English clinical texts, but less dealt with clinical notes in languages other than English. This study tested the feasibility of using 'off the shelf' information extraction algorithms to identify medical concepts from Italian clinical notes. We used MetaMap to map medical concepts to the Unified Medical Language System (UMLS). The study addressed two questions: (Q1) to understand if it would be possible to properly map medical terms found in clinical notes and related to the semantic group of 'Disorders' to the Italian UMLS resources; (Q2) to investigate if it would be feasible to use MetaMap as it is to extract these medical concepts from Italian clinical notes. Results in EXP1 showed that the Italian UMLS Metathesaurus sources covered 91% of the medical terms of the 'Disorders' semantic group, as found in the studied dataset. Even if MetaMap was built to analyze texts written in English, it worked properly also with texts written in Italian. MetaMap identified correctly about half of the concepts in the Italian clinical notes. Using MetaMap's annotation on Italian clinical notes instead of a simple text search improved our results of about 15 percentage points. MetaMap showed recall, precision and F-measure of 0.53, 0.98 and 0.69, respectively. Most of the failures were due to the impossibility for MetaMap to generate Italian meaningful variants. MetaMap's performance in annotating automatically translated English clinical notes was in line with findings in the literature, with similar recall (0.75), F-measure (0.83) and even higher precision (0.95)., This paper has been published in the Journal of biomedical informatics, Volume 63, October 2016, Pages 22-32

This paper presents an enhanced version of an interactive video retrieval tool SOMHunter that won Video Browser Showdown 2020. The presented enhancements focus on improving text querying capabilities since the text search model plays a crucial part in successful searches. Hence, we introduce the ability to specify multiple text queries with further positional specification so users can better describe positional relationships of the objects. Moreover, a possibility to further specify text queries with an example image is introduced as well as consequent changes to the user interface of the tool.

The growing number of undergraduated thesis produced at the end of undergraduated courses in Brazil are sometimes available only in physical libraries or have limited digital access, making it difficult for researchers and the general population to access this information. This paper presents the development of a system that uses data analysis and information retrieval techniques capable of providing full-text search, as well as the recommendation of works based on their similarity using the Latent Dirichlet Allocation (LDA) technique. The goal of this solution is to offer higher education institutions in Brazil a platform capable of providing digital access to the documents they produced, enabling the dissemination of scientific production. The tool was validated using data from a real educational institution, and the search and recommendation mechanisms proved to be efficient for their purpose.

This paper evaluates the Couchbase Server platform performance for storing data items, using NoSQL databases. It involved services for querying and indexing, both deployed in Microsoft Azure Cloud environment and virtual machines. The architecture contained three virtual machines acting as nodes for the Couchbase Server database. Deploying and establishing the database in the public cloud was done with Docker images. Some of the key features and applications from Microsoft Azure were tested, i.e. Monitor, Resource groups, Dashboard and Storage accounts. From the Couchbase perspective, its friendly usage with full text search and real-time analytics proved to be useful for processing of big data.

Keeping up with the rapid growth of Deep Learning (DL) research is a daunting task. While existing scientific literature search systems provide text search capabilities and can identify similar papers, gaining an in-depth understanding of a new approach or an application is much more complicated. Many publications leverage multiple modalities to convey their findings and spread their ideas - they include pseudocode, tables, images and diagrams in addition to text, and often make publicly accessible their implementations. It is important to be able to represent and query them as well. We utilize RDF Knowledge graphs (KGs) to represent multimodal information and enable expressive querying over modalities. In our demo we present an approach for extracting KGs from different modalities, namely text, architecture images and source code. We show how graph queries can be used to get insights into different facets (modalities) of a paper, and its associated code implementation. Our innovation lies in the multimodal nature of the KG we create. While our work is of direct interest to DL researchers and practitioners, our approaches can also be leveraged in other scientific domains.

As reported by respected evaluation campaigns focusing both on automated and interactive video search approaches, deep learning started to dominate the video retrieval area. However, the results are still not satisfactory for many types of search tasks focusing on high recall. To report on this challenging problem, we present two orthogonal task-based performance studies centered around the state-of-the-art W2VV++ query representation learning model for video retrieval. First, an ablation study is presented to investigate which components of the model are effective in two types of benchmark tasks focusing on high recall. Second, interactive search scenarios from the Video Browser Showdown are analyzed for two winning prototype systems implementing a selected variant of the model and providing additional querying and visualization components. The analysis of collected logs demonstrates that even with the state-of-the-art text search video retrieval model, it is still auspicious to integrate users into the search process for task types, where high recall is essential.

In the last decade, the Video Browser Showdown (VBS) became a comparative platform for various interactive video search tools competing in selected video retrieval tasks. However, the participation of new teams with an own, novel tool is prohibitively time-demanding because of the large number and complexity of components required for constructing a video search system from scratch. To partially alleviate this difficulty, we provide an open-source version of the lightweight known-item search system SOMHunter that competed successfully at VBS 2020. The system combines several features for text-based search initialization and browsing of large result sets; in particular a variant of W2VV++ model for text search, temporal queries for targeting sequences of frames, several types of displays including the eponymous self-organizing map view, and a feedback-based approach for maintaining the relevance scores inspired by PICHunter. The minimalistic, easily extensible implementation of SOMHunter should serve as a solid basis for constructing new search systems, thus facilitating easier exploration of new video retrieval ideas.

The usability of digital information on the internet strongly depends on its searchability. There are search engines for global language based text search, but language based information representation has only limited value, e.g. concerning reproducibility, comparability, precision. Searchable digital information can be much more. Any piece of digital information is a number sequence. We can define the binary format and value set resp. domain of every number online. Then universal information transport is possible by the online defined "Domain Vector" (DV) data structure: "UL plus number sequence". At this "UL" is an efficient link to the machine readable online definition of the number sequence. The UL also is global identifier of a certain kind of data. The online definition includes additional information, e.g. for similarity comparison of the number sequence. With this a universal numeric search engine can provide precise user defined worldwide search of DVs like in a globalized database. All users can participate. Together we can optimize online definitions and provide defined data as DVs. Initially it is necessary to build a first attractive online presence where users can provide online definitions. We should stay in contact to optimize together the common standard for machine readable online definitions and DVs.

Traditional search through collections of audio recordings compares a text-based query to text metadata associated with each audio file and does not address the actual content of the audio. Text descriptions do not describe all aspects of the audio content in detail. Query by vocal imitation (QBV) is a kind of query by example that lets users imitate the content of the audio they seek, providing an alternative search method to traditional text search. Prior work proposed several neural networks, such as TL-IMINET, for QBV, however, previous systems have not been deployed in an actual search engine nor evaluated by real users. We have developed a state-of-the-art QBV system (Vroom!) and a baseline query-by-text search engine (TextSearch). We deployed both systems in an experimental framework to perform user experiments with Amazon Mechanical Turk (AMT) workers. Results showed that Vroom! received significantly higher search satisfaction ratings than TextSearch did for sound categories that were difficult for subjects to describe by text. Results also showed a better overall ease-of-use rating for Vroom! than TextSearch on the sound library used in our experiments. These findings suggest that QBV, as a complimentary search approach to existing text-based search, can improve both search results and user experience.

Introduction: Most cohort studies are limited by sampling and accrual bias. The capability to detect specific lesions identified in radiological text reports could eliminate these biases and benefit patient care, clinical research, and trial recruitment. This study derived and internally validated text search algorithms to identify four common urological lesions (solid renal masses, complex renal cysts, adrenal masses, and simple renal cysts) using radiology text reports. Methods: A simple random sample of 10 000 abdominal ultrasound (US) and computed tomography (CT) reports was drawn from our hospital’s data warehouse. Reports were manually reviewed to determine the true status of the four lesions. Using commonly available software, we created logistic regression models having as predictors the status of a priori selected text terms in the report. We used bootstrap sampling with 95th percentile thresholds to select variables for the final models, which were modified into point systems. A second independent, random sample of 2855 reports, stratified by the number of points for each abnormality, was reviewed in a blinded fashion to measure the accuracy of each lesion’s point system. Results: The prevalence of solid renal mass, complex renal cyst, adrenal mass and simple renal cyst, was 2.0%, 1.7%, 3.2%, and 20.0%, respectively. Each model contained between one and five text terms with c-statistics ranging between 0.66 and 0.90. In the independent validation, the scoring systems accurately predicted the probability that a text report cited the four lesions. Conclusions: Textual radiology reports can be analyzed using common statistical software to accurately determine the probability that important abnormalities of the kidneys or adrenal glands exist. These methods can be used for case identification or epidemiological studies.

This paper presents the Shark look calculation utilizing the refined form of PageRank calculation, "PageRank look" and Shark look, one of the primary energetic web look calculations. Shark search has a comprehensive database mapping system that makes it easy for users to customize online maps to suit their needs. Preparatory tests appear significant improvements over the initial calculation of page rank. Recently, the internet has grown a lot. By using different hypertext connections, users can find their tools. This Internet use led to web crawlers being invented. Web-based crawlers are full text search engines that support web browsers. Such web crawlers can be used for further study. For example, the broken information can be utilized in complex systems to discover lost connections, population identification. In this paper we discussed web crew members: their design, styles and different challenges when the Web crawlers are used by search engines.

BackgroundCentral line associated pneumothorax (CLAP) could be a good quality of care indicator because they are objectively measured, clearly undesirable and possibly avoidable. We measured the incidence and trends of CLAP using radiograph report text search with manual review and compared them with measures using routinely collected health administrative data.MethodsFor each hospitalisation to a tertiary care teaching hospital between 2002 and 2015, we searched all chest radiography reports for a central line with a sensitive computer algorithm. Screen positive reports were manually reviewed to confirm central lines. The index and subsequent chest radiography reports were screened for pneumothorax followed by manual confirmation. Diagnostic and procedural codes were used to identify CLAP in administrative data.ResultsIn 685 044 hospitalisations, 10 819 underwent central line insertion (1.6%) with CLAP occurring 181 times (1.7%). CLAP risk did not change over time. Codes for CLAP were inaccurate (sensitivity 13.8%, positive predictive value 6.6%). However, overall code-based CLAP risk (1.8%) was almost identical to actual values possibly because patient strata with inflated CLAP risk were balanced by more common strata having underestimated CLAP risk. Code-based methods inflated central line incidence 2.2 times and erroneously concluded that CLAP risk decreased significantly over time.ConclusionsUsing valid methods, CLAP incidence was similar to those in the literature but has not changed over time. Although administrative database codes for CLAP were very inaccurate, they generated CLAP risks very similar to actual values because of offsetting errors. In contrast to those from radiograph report text search with manual review, CLAP trends decreased significantly using administrative data. Hospital CLAP risk should not be measured using administrative data.

Raster-image PDF files originating from scanning or photographing paper documents are inaccessible to both text search engines and screen readers that people with visual impairments use. We here focus on the relatively less-researched problem of converting raster-image files with Arabic script into machine-accessible documents. Our method, called ECDP for "Ensemble-based classification of document patches," segments the physical layout of the document, classifies image patches as containing text or graphics, assembles homogeneous document regions, and passes the text to an optical character recognition engine to convert into natural language. Classification is based on the majority voting of an ensemble of support vector machines. When tested on the dataset BCE-Arabic [Saad et al. in: ACM 9th annual international conference on pervasive technologies related to assistive environments (PETRA'16), Corfu, 2016], ECDP yielded an average patch classification accuracy of 97.3% and average $$F_1$$F1 score of 95.26% for text patches and efficiently extracted text zones in both paragraphs and text-embedded graphics, even if the text is rotated by $$90^{\circ }$$90ź or is in English. ECDP outperforms a classical layout analysis method (RLSA) and a state-of-the-art commercial product (RDI-CleverPage) on this dataset and maintains a relatively high level of performance on document images drawn from two other datasets (Hesham et al. in Pattern Anal Appl 20:1275---1287, 2017; Proprietary Dataset of 109 Arabic Documents. http://www.rdi-eg.com). The results suggest that the proposed method has the potential to generalize well to the analysis of documents with a broad range of content.

Voice is the most natural way for humans to communicate with each other, and more recently, to interact with voice controlled digital machines. Although text is predominant in digital platforms, voice and video are becoming increasingly important, with communication applications supporting voice messages and videos. This is relevant for digital forensic examinations, as content held in voice format can hold relevant evidence for the investigation. In this paper, we present the open source SpeechToText software, which resorts to state-of-the art Voice Activity Detection (VAD) and Automatic Speech Recognition (ASR) modules to detect voice content, and then to transcribe it to text. This allows integrating voice content into the regular flow of a digital forensic investigation, with transcribed audio indexed by text search engines. Although SpeechToText can be run independently, it also provides a Jython-based software module for the well-known Autopsy software. The paper also analyzes the availability, storage location and audio format of voice-recorded content in 14 popular Android applications featuring voice recordings. SpeechToText achieves 100% accuracy for detecting voice in unencrypted audio/video files, a word error rate (WER) of 27.2% when transcribing English voice messages by non-native speakers and a WER of 7.80% for the test-clean set of LibriSpeech. It achieves a real time factor of 0.15 for the detection and transcription process in a medium-range laptop, meaning that 1 min of speech is processed in roughly 9 s.

More and more information on tourist spots is being represented as pictures rather than text. Consequently, tourists who are interested in a specific attraction shown in pictures may have no idea how to perform a text search to get more information about the interesting tourist spots. In the view of this problem and to enhance the competitiveness of the tourism market, this research proposes an innovative tourist spot identification mechanism, which is based on deep learning-based object detection technology, for real-time detection and identification of tourist spots by taking pictures on location or retrieving images from the Internet. This research establishes a tourist spot recognition system, which is a You Only Look Once version 3 model built in Tensorflow AI framework, and is used to identify tourist attractions by taking pictures with a smartphone's camera. To verify the possibility, a set of tourist spots in Hsinchu City, Taiwan is taken as an example. Currently, the tourist spot recognition system of this research can identify 28 tourist spots in Hsinchu. In addition to the attraction recognition feature, tourists can further use this tourist spot recognition system to obtain more information about 77 tourist spots from the Hsinchu City Government Information Open Data Platform, and then make dynamic travel itinerary planning and Google MAP navigation. Compared with other deep learning models using Faster region-convolutional neural networks or Single-Shot Multibox Detector algorithms for the same data set, the recognition time by the models using You Only Look Once version 3, Faster region-convolutional neural networks, and Single-Shot Multibox Detector algorithms are respectively 4.5, 5, and 9 s, and the mean average precision for each when IoU = 0.6 is 88.63%, 85%, and 43.19%, respectively. The performance experimental results of this research show the model using the You Only Look Once version 3 algorithm is more efficient and precise than the models using the Faster region-convolutional neural networks or the Single-Shot Multibox Detector algorithms, where You Only Look Once version 3 and Single-Shot Multibox Detector are one-stage learning architectures with efficient features, and Faster region-convolutional neural networks is a two-stage learning architecture with precise features.

This work is aimed to develop a system, that will effectively solve the problem of storing and analyzing files containing text data, by using modern software development tools, techniques and approaches. The main challenge of storing a large number of text documents defined at the problem formulation stage, have to be resolved with such functionality as full text search and document clustering depends on their contents. Main system features could be described with notions of distributed multilevel architecture, flexibility and interchangeability of components, achieved through the standard functionality incapsulation in independent executable modules.

We provide a quality evaluation of KB+Text search, a deep integration of knowledge base search and standard full-text search. A knowledge base (KB) is a set of subject–predicate–object triples with a common naming scheme. The standard query language is SPARQL, where queries are essentially lists of triples with variables. KB+Text search extends this by a special occurs-with predicate, which can be used to express the co-occurrence of words in the text with mentions of entities from the knowledge base. Both pure KB search and standard full-text search are included as special cases. We evaluate the result quality of KB+Text search on three different query sets. The corpus is the full version of the English Wikipedia (2.4 billion word occurrences) combined with the YAGO knowledge base (26 million triples). We provide a web application to reproduce our evaluation, which is accessible via http://ad.informatik.uni-freiburg.de/publications .

Word stemming is a linguistic process in which the various inflected word forms are matched to their base form. It is among the basic text pre-processing approaches used in Natural Language Processing and Information Retrieval. Stemming is employed at the text pre-processing stage to solve the issue of vocabulary mismatch or to reduce the size of the word vocabulary, and consequently also the dimensionality of training data for statistical models. In this article, we present a fully unsupervised corpus-based text stemming method which clusters morphologically related words based on lexical knowledge. The proposed method performs cognitive-inspired computing to discover morphologically related words from the corpus without any human intervention or language-specific knowledge. The performance of the proposed method is evaluated in inflection removal (approximating lemmas) and Information Retrieval tasks. The retrieval experiments in four different languages using standard Text Retrieval Conference, Cross-Language Evaluation Forum, and Forum for Information Retrieval Evaluation collections show that the proposed stemming method performs significantly better than no stemming. In the case of highly inflectional languages, Marathi and Hungarian, the improvement in Mean Average Precision is nearly 50% as compared to unstemmed words. Moreover, the proposed unsupervised stemming method outperforms state-of-the-art strong language-independent and rule-based stemming methods in all the languages. Besides Information Retrieval, the proposed stemming method also performs significantly better in inflection removal experiments. The proposed unsupervised language-independent stemming method can be used as a multipurpose tool for various tasks such as the approximation of lemmas, improving retrieval performance or other Natural Language Processing applications.

This paper is intended to present the implementation and testing methodology of transductive support vector machines (TSVM) proposed by Joachims et al [1]. Initially it explains the concept offering by the Support Vector Machines as optimal classifiers and clarifies the concept of transductive inference. Along the implementation process several tests were performed. The data used for such tests was very diverse especially with respect to the dimensionality (number of samples, features,etc.). The ultimate objective was to integrate the Transductive inference tool in the already developed Intelligent Interface Web Engine [2] from the SISTA group at the Catholic University of Leuven (Belgium) [2].

Massive taxi trajectory data is exploited for knowledge discovery in transportation and urban planning. Existing tools typically require users to select and brush geospatial regions on a map when retrieving and exploring taxi trajectories and passenger trips. To answer seemingly simple questions such as "What were the taxi trips starting from Main Street and ending at Wall Street in the morning?" or "Where are the taxis arriving at the Art Museum at noon typically coming from?", tedious and time consuming interactions are usually needed since the numeric GPS points of trajectories are not directly linked to the keywords such as "Main Street", "Wall Street", and "Art Museum". In this paper, we present SemanticTraj, a new method for managing and visualizing taxi trajectory data in an intuitive, semantic rich, and efficient means. With SemanticTraj, domain and public users can find answers to the aforementioned questions easily through direct queries based on the terms. They can also interactively explore the retrieved data in visualizations enhanced by semantic information of the trajectories and trips. In particular, taxi trajectories are converted into taxi documents through a textualization transformation process. This process maps GPS points into a series of street/POI names and pick-up/drop-off locations. It also converts vehicle speeds into user-defined descriptive terms. Then, a corpus of taxi documents is formed and indexed to enable flexible semantic queries over a text search engine. Semantic labels and meta-summaries of the results are integrated with a set of visualizations in a SemanticTraj prototype, which helps users study taxi trajectories quickly and easily. A set of usage scenarios are presented to show the usability of the system. We also collected feedback from domain experts and conducted a preliminary user study to evaluate the visual system.

While maintaining a food record is an essential means of health management, there has long been a reliance on conventional methods, such as entering text into record sheets, in the health medicine field. Food recording is a time-consuming activity; hence, there is a need for innovation using information technology. We have developed the smartphone application “FoodLog,” as a new framework for food recording. This application uses digital pictures and is supported by image recognition and searches. It is available for general release. In this paper, we present an overview of this framework, the data statistics obtained using FoodLog, and the future prospects of this application.

In cloud computing, the end user stored their files with minimum maintenance cost, where cloud servers provide the file storage facility to analyze their outsourced data. However, security of the data is a major concern of the end user, because unauthorized person may access the data in cloud. The end-user should encrypt the files for providing data usability and privacy, before outsourcing to the cloud. The main aim of the research work is to secure the outsourced file data in cloud and only the end user can able to access those files from cloud storage system. This research aims to apply Merkle Hash Tree (MHT) to store the encrypted data with the hash value to increase the efficiency of the search process. The application of this method in cloud search engine to search the encrypted data with increasing retrieval efficiency. In multiuser system, to prevent the unauthorized access of data, fine-grained access control plays a major role in cloud. But, some authorized user may leak the secret key purposefully for financial benefits. To overcome these challenging issues, this research work implements the privacy-preserving Multi-keyword Text Search (MTS) with a similarity-based ranking method. Also, two secure index schemes namely known background and cipher text model are developed to enhance the search privacy. When compared with the linear search, the search efficiency is further improved by implementing the MHT. The experiments are conducted to validate the efficiency of the proposed method with existing techniques. The proposed MTS-MHT technique achieved 99.95% retrieval accuracy with minimum searching time (i.e. 80sec) for the various number of files, when compared with traditional encryption techniques.

This paper proposes a new approach to find the most relevant solution for growers' problems. The proposed approach utilized the full-text search of Microsoft SQL Server to index and search growers' problems. Also, it integrates the expert system with the result of full-text search by annotating the results with tips for more information, in addition to indexing the knowledge base and applying full-text search on it. We applied the proposed approach in VERCON's growers' problems module; this module contains a database of growers' problems for different crops. The experiments have been applied on wheat, a dataset of 874 problems. The results clearly indicate that the proposed approach is capable to retrieve the most relevant solution at the top 5 rankings with a high degree of accuracy.

Leaflets are one of the most straightforward methods for obtaining details regarding how to administer drugs, their composition, warnings, or precautions in their usage. However, they are many times cluttered with information, making them hard to understand by people. At the same time, the provided indications are frequently either too specific or too broad, thus making their understanding even more difficult. This paper presents the architecture and the prototype of an intelligent platform for drug administration with the following key functionalities: adding specific medications to user’s profile, searching for potential contraindications or side effects, and defining alerts of drug administration in the provided calendar, based on the physician’s prescription. The platform aggregates leaflets from two sources (Biofarm and HelpNet) using Natural Language Processing (NLP) techniques tailored for Romanian language and provides full-text search via Elasticsearch. A friendly mobile application, available for IOS and Android devices, as well as in web browsers, was developed to improve users’ healthcare and ensure self-education.

Thesis deals with automated corpus development techniques for specific linguistic research purposes. Different corpora and corpus toolboxes available today have been overviewed. Corpus tool functionality for processing custom and private text purposes and automated corpora building system capabilities has been classified. Lack of analytical means which decrease effectiveness, multifunctionality and adaptability in overviewed corpora has been illustrated (impossibility of FrameNet usage, lack of detailed statistics and other relevant issues). Main stages of source data text processing have been reviewed. Natural language processing and natural language understanding methods and tools for adaptable corpora building have been examined and justified. General workflow and design of adaptable text corpus software tool are suggested. Adaptable text corpus software prototype for specific linguistic research purposes has been developed. Big Data and text search engine approaches have been implemented in the prototype.

This paper describes a software tool called Text Search, which allows you to identify a plurality of content based on a thematic analysis of the text. It works with English fiction texts. Input is a user's query in English in the form of a text that is subject to thematic analysis and compared with the thematic analysis of texts in the database. This program is a database that stores, processes and issues information at the same time. The interface is implemented using the C # language and Windows Forms components, a database with a specific language, Transact-SQL, which was created jointly between Microsoft and Sybase. This language is an alternative to SQL with more advanced functionality. Modeling an information system is an important process that allows you to make a qualitative assessment of the scale of the system, to examine all its processes, the data to be used, and communications. By demonstrating the use of different types of diagrams, the main purpose of the system's operation is identified: the identification of a plurality of content based on a thematic analysis of similar texts. A hierarchical sequence of temporary objectives which lead to the accomplishment of the main goal is presented. The main processes of the information system and the data flows that it uses are demonstrated. Sub-processes are demonstrated at the second level of decomposition. In addition, a tree-like structure of the process hierarchy is created. It demonstrates the main processes and tasks that arise during their implementation, as well as their relationship.

Logs are imperative in the development and maintenance process of many software systems. They record detailed runtime information that allows developers and support engineers to monitor their systems and dissect anomalous behaviors and errors. The increasing scale and complexity of modern software systems, however, make the volume of logs explodes. In many cases, the traditional way of manual log inspection becomes impractical. Many recent studies, as well as industrial tools, resort to powerful text search and machine learning-based analytics solutions. Due to the unstructured nature of logs, a first crucial step is to parse log messages into structured data for subsequent analysis. In recent years, automated log parsing has been widely studied in both academia and industry, producing a series of log parsers by different techniques. To better understand the characteristics of these log parsers, in this paper, we present a comprehensive evaluation study on automated log parsing and further release the tools and benchmarks for easy reuse. More specifically, we evaluate 13 log parsers on a total of 16 log datasets spanning distributed systems, supercomputers, operating systems, mobile systems, server applications, and standalone software. We report the benchmarking results in terms of accuracy, robustness, and efficiency, which are of practical importance when deploying automated log parsing in production. We also share the success stories and lessons learned in an industrial application at Huawei. We believe that our work could serve as the basis and provide valuable guidance to future research and deployment of automated log parsing., Comment: This paper is accepted in International Conference on Software Engineering (ICSE'19)

This paper presents an approach for full-text search of files stored in MongoDB database and GridFS system. This solution contains an API Rest interface that processes the requests and provides all business logic and MongoDB database that provides storage features. Besides, the simple web application has built to illustrate the usage of the system. The implemented solution has no dependency on any other full-text engine and it is implemented on its own. The proposed system can be integrated into any document management system or enterprise application system to provide the feature of searching content in stored files based on free form text.

ObjectiveElectronic health record (EHR) systems contain structured data and unstructured documentation. Clinical insights can be derived from analyzing both but optimal methods for this have not been studied extensively. We compared various approaches to analyzing EHR data for non-alcoholic fatty liver disease (NAFLD).Materials and MethodsWe compared analysis of structured and unstructured EHR data using natural language processing (NLP), free-text search, and diagnostic codes against expert adjudication as the reference standard.ResultsOut of 38,575 patients, we identified 2,281 patients with NAFLD. From the remainder, 10,653 patients with similar data density were selected as a control group. NLP was more sensitive than ICD and text search (NLP 0.93 vs. ICD 0.28 vs. text search 0.81) with higher a F2 score (NLP 0.92 vs. ICD 0.34 vs. text search 0.81). 619 patients had suspected NAFLD documented in radiology notes not acknowledged in other forms of clinical documentation. Of these, 232 (37.5%) were found to have more advanced liver disease after a median of 1,057 days.DiscussionNLP-based approaches have superior accuracy in identifying NAFLD within the EHR compared to ICD/text search-based approaches. Suspected NAFLD on imaging is often not acknowledged in subsequent clinical documentation. Many such patients are later found to have more advanced liver disease.ConclusionFor identification of NAFLD, NLP performed better than alternative selection modalities and facilitated follow-on analysis of information flow. If accuracy can be proven to persist across clinical domains, NLP can identify patient phenotypes for biomedical research in an accurate and high-throughput manner.

Since the 1970’s the Content-Based Image Indexing and Retrieval (CBIR) has been an active area. Nowadays, the rapid increase of video data has paved the way to the advancement of the technologies in many different communities for the creation of Content-Based Video Indexing and Retrieval (CBVIR). However, greater attention needs to be devoted to the development of effective tools for video search and browse. In this paper, we present Visione, a system for large-scale video retrieval. The system integrates several content-based analysis and retrieval modules, including a keywords search, a spatial object-based search, and a visual similarity search. From the tests carried out by users when they needed to find as many correct examples as possible, the similarity search proved to be the most promising option. Our implementation is based on state-of-the-art deep learning approaches for content analysis and leverages highly efficient indexing techniques to ensure scalability. Specifically, we encode all the visual and textual descriptors extracted from the videos into (surrogate) textual representations that are then efficiently indexed and searched using an off-the-shelf text search engine using similarity functions.

Now with the application of Snap videos or short videos, both those obtained from social media such as Instagram, Twitter, and Facebook, there are many pieces of audio and video files of short duration which contain songs that have meaning. When we are interested in knowing a song, we have a hard time finding out the title of the song or the source. We designed an application to identify cognitive-based songs using a prototype method to overcome these problems. The method we use is a prototype model, this method is a paradigm in software creation and development, we chose this method because the process is relatively faster because it uses mock ups in its application. From the test results, the song identification application that we made is very effective for identifying the types of songs with slow genres such as jazz, blues, and acoustic but less effective for hard rock and RnB songs.

We used big data software Hadoop in Google News to collect complex high-velocity, high-volume terrorism information. We used big text search to code the factors of interest into nominal fields. We integrated new fields and records into an existing database drawn from other researchers. Our testable hypothesis was that there was a significant relationship between terrorist group ideology and terrorist attack type. Then we used correspondence analysis in SPSS to test our hypothesis. Our hypothesis was supported, so we developed a symmetric model to visualize the hidden relationships between terrorist ideology and attack type. Our purpose was to demonstrate how statistical software methods may be applied in big data analytics. These methods will generalize to other researchers and practitioners. The finding of a significant relationship between terrorist ideology and attack type may generalize to supply chain operations and national security planning.

Privacy policies describe high-level goals for corporate data practices; regulators require industries to make available conspicuous, accurate privacy policies to their customers. Consequently, software requirements must conform to those privacy policies. To help stakeholders extract privacy goals from policies, we introduce a semiautomated framework that combines crowdworker annotations, natural language typed dependency parses, and a reusable lexicon to improve goal-extraction coverage, precision, and recall. The framework evaluation consists of a five-policy corpus governing web and mobile information systems, yielding an average precision of 0.73 and recall of 0.83. The results show that no single framework element alone is sufficient to extract goals; however, the overall framework compensates for elemental limitations. Human annotators are highly adaptive at discovering annotations in new texts, but those annotations can be inconsistent and incomplete; dependency parsers lack sophisticated, tacit knowledge, but they can perform exhaustive text search for prospective requirements indicators; and while the lexicon may never completely saturate, the lexicon terms can be reliably used to improve recall. Lexical reuse reduces false negatives by 41%, increasing the average recall to 0.85. Last, crowd workers were able to identify and remove false positives by around 80%, which improves average precision to 0.93.

Visual access to the content in digital archives extends the classical text search and list view of graphical user interfaces. Currently, there are several strategies employed to correlate images in the user interface of digital archives for semantic purposes. Some of the most useful strategies explore innovative techniques used to gain and execute metadata in a suitable manner. These approaches are elaborated on primarily in the context of scientific questions. Amidst these models, this article proposes a very simple strategy of networking images using only words. At present, this concept is realised at Zurich University of the Arts (ZHdK) through utilisation of the ‘Media Archive of the Arts’, an in-house, open source software product. It responds to user heterogeneity, the variety of intellectual genres and the multiplicity of media formats that are distinctive of an art academy such as ZHdK.