Extracting Room Prices from Web Tables — an Ontology-Aware Approach

Information extraction from semi-structured webpages provides valuable long-tailed facts for augmenting knowledge graph. Relational Web tables are a critical component containing additional entities and attributes of rich and diverse knowledge. However, extracting knowledge from relational tables is challenging because of sparse contextual information. Existing work linearize table cells and heavily rely on modifying deep language models such as BERT which only captures related cells information in the same table. In this work, we propose a novel relational table representation learning approach considering both the intra- and inter-table contextual information. On one hand, the proposed Table Convolutional Network model employs the attention mechanism to adaptively focus on the most informative intra-table cells of the same row or column; and, on the other hand, it aggregates inter-table contextual information from various types of implicit connections between cells across different tables. Specifically, we propose three novel aggregation modules for (i) cells of the same value, (ii) cells of the same schema position, and (iii) cells linked to the same page topic. We further devise a supervised multi-task training objective for jointly predicting column type and pairwise column relation, as well as a table cell recovery objective for pre-training. Experiments on real Web table datasets demonstrate our method can outperform competitive baselines by +4.8% of F1 for column type prediction and by +4.1% of F1 for pairwise column relation prediction.

Traditionally, information extraction from web tables has focused on small, more or less homogeneous corpora, often based on assumptions about the use of tags. A multitude of different HTML implementations of web tables make these approaches difficult to scale. In this paper, we approach the problem of domain-independent information extraction from web tables by shifting our attention from the tree-based representation of webpages to a variation of the two-dimensional visual box model used by web browsers to display the information on the screen. The there by obtained topological and style information allows us to fill the gap created by missing domain-specific knowledge about content and table templates. We believe that, in a future step, this approach can become the basis for a new way of large-scale knowledge acquisition from the current Visual Web.

Monitoring and management of large scale applications is already a complex task because of syntactic and unstructured nature of execution data. Traditional application monitoring and management solutions focused on employing analysis techniques on unstructured and syntactic log information become limited as unstructured information cannot be well utilized to find out related events information or correlate such information with other related information from applications. Our proposed solution of semantically formalized logging fills this gap by bringing formal semantics and combining it in a meaningful way to enable automated monitoring and management of applications. Such formalized and well-structured log information helps analytical solution to maximally automate the process of monitoring and management of applications. However, while formalizing and structuring the log information, we came across several missing and incomplete data which causes hindrance in this process. In this paper, we tackle this problem and propose a social network analysis based solution to handle incomplete and missing data from application execution, possibly compute it and use it by our proposed solution of semantically formalizing and structured logs with adapted data mining techniques to enable automated and effective application monitoring and management. We demonstrate from an industrial use-case application that how historical data from application execution is stored using semantic logging and utilized with standard social-network analysis techniques to find out missing values in incomplete data and perform application monitoring and management.

Information extraction (IE) is a technique for extracting structured data or knowledge from unstructured data by determining the references to words as well as the relationships between them. IE systems can be used to directly extract knowledge from a text corpus, or to extract useful data from a pile of documents which moreover, can be further analyzed with deep learning algorithms to discover more patterns. In today's era, the internet exhibits several characteristics including unstructured data and noisy text information. Unstructured data may contain audio, image, text, video, etc. Information extraction can be useful for topic detection (Twitter, Digital libraries), Breast Cancer detection and many more applications. The proposed system can exploit deep learning for information extraction using image as well as text and can significantly improve its performance with the inclusion of structured and unstructured data. This paper focuses on extraction of information from unstructured data using various deep learning models and concepts of Natural Language Processing (NLP), Long Short Term Networks (LSTM) and for topic extraction used Latent Dirichlet Allocation (LDA) etc.

The emergence of the digital era has led to growth in various types of data in a cloud. In fact, there may be three fourth of the total data will be treated as big data. In many organisations, massive volume of both structured and unstructured data sit idle. Various categories of data are complex for pre-processing, analysing, storing and visualising. Cloud computing provides suitable platform for big data analytics for the storage and for predicting customer behaviour to sell products. Unstructured data like emails, notes, messages, documents, notifications and Twitter comments (including from IoT devices) remains untapped and is not stored in a relational database. Valuable information on pricing, customer behaviour and competitors may be inhumed within unstructured data. This makes cloud-based analytics as an effective research field to address several issues and risks need to be reduced. So we propose a method to extract and cluster sentiment information from various types of unstructured text data from social networks by using SVM classifiers combined with lexicons and machine learning for sentiment analysis of customer behaviour feedback. The method has performed efficient data collection, data loading and efficiently performs sentiment analysis on deep and hidden web.

The availability of massive sets of unstructured data has opened up new opportunities for businesses to gain meaningful insights into what is currently happening in their organization and market place. Unfortunately, unstructured data is often challenging to work with, as it requires specialized toolsets, techniques, knowledge and skills to engage with the data. This study used a systematic review (SLR) process to explore the current and conversant state of affairs in the field of text mining (TM) techniques that exist for the processing of natural language in unstructured text datasets across a broad expanse of applications and domains. A comprehensive literature search yielded 1022 eligible articles from five prominent bibliographic databases, narrowed down to 89 articles for review. Information related to TM techniques, the TM process, applications, challenges and recommendations for the improvement of TM results were extracted and synthesized. Eighteen TM techniques were identified and used to complete a variety of tasks such as data pre-processing, information retrieval, information extraction, text classification, clustering, topic modeling, text summarization and sentiment analysis or opinion mining. No single TM technique may be suitable for all text representation and extraction requirements. Therefore, context and applicability are key factors for TM technique selection.KeywordsText miningText mining techniquesUnstructured dataKnowledge discovery

SummaryBackground:Clinical Data Warehouses (CDW) reuse Electronic health records (EHR) to make their data retrievable for research purposes or patient recruitment for clinical trials. However, much information are hidden in unstructured data like discharge letters. They can be preprocessed and converted to structured data via information extraction (IE), which is unfortunately a laborious task and therefore usually not available for most of the text data in CDW.Objectives:The goal of our work is to provide an ad hoc IE service that allows users to query text data ad hoc in a manner similar to querying structured data in a CDW. While search engines just return text snippets, our systems also returns frequencies (e.g. how many patients exist with “heart failure” including textual synonyms or how many patients have an LVEF < 45) based on the content of discharge letters or textual reports for special investigations like heart echo. Three subtasks are addressed: (1) To recognize and to exclude negations and their scopes, (2) to extract concepts, i.e. Boolean values and (3) to extract numerical values.Methods:We implemented an extended version of the NegEx-algorithm for German texts that detects negations and determines their scope. Furthermore, our document oriented CDW PaDaWaN was extended with query functions, e.g. context sensitive queries and regex queries, and an extraction mode for computing the frequencies for Boolean and numerical values.Results:Evaluations in chest X-ray reports and in discharge letters showed high F1-scores for the three subtasks: Detection of negated concepts in chest X-ray reports with an F1-score of 0.99 and in discharge letters with 0.97; of Boolean values in chest X-ray reports about 0.99, and of numerical values in chest X-ray reports and discharge letters also around 0.99 with the exception of the concept age.Discussion:The advantages of an ad hoc IE over a standard IE are the low development effort (just entering the concept with its variants), the promptness of the results and the adaptability by the user to his or her particular question. Disadvantage are usually lower accuracy and confidence.This ad hoc information extraction approach is novel and exceeds existing systems: Roogle [1] extracts predefined concepts from texts at preprocessing and makes them retrievable at runtime. Dr. Warehouse [2] applies negation detection and indexes the produced subtexts which include affirmed findings. Our approach combines negation detection and the extraction of concepts. But the extraction does not take place during preprocessing, but at runtime. That provides an ad hoc, dynamic, interactive and adjustable information extraction of random concepts and even their values on the fly at runtime.Conclusions:We developed an ad hoc information extraction query feature for Boolean and numerical values within a CDW with high recall and precision based on a pipeline that detects and removes negations and their scope in clinical texts.

Currently, there are a large number of hotel Web sites that develop their own seals of quality based on customer feedback. As a result, a hotel can be classified differently by various Web sites at the same time, creating confusion in the consumer perceptions about the quality of a given hotel. Moreover, there are attempts to standardize such service quality evaluation, such as the SERVQUAL instrument, which is a multiple-item scale for measuring service quality with several dimensions. In this context, we present a two-stage linguistic multicriteria decision-making model to integrate the hotel guests' opinions included in several Web sites, with two objectives: on the one hand, obtaining a SERVQUAL scale evaluation value of service quality with the integrated answers of the input opinions; on the other hand, getting a SERVQUAL overall evaluation value of service quality. This model is incorporated into an opinion aggregation architecture to integrate heterogeneous data (natural language included) from various tourism Web sites. As a particular case study, we show an application example using the high-end hotels located in Granada (Spain).© 2012 Wiley Periodicals, Inc. © 2012 Wiley Periodicals, Inc.

Information Extraction (IE) is the key technology enabling analytics over unstructured and semi-structured data. Not surprisingly, it is becoming a critical building block for a wide range of emerging applications. To satisfy the rising demands for information extraction in real-world applications, it is crucial to lower the barrier to entry for IE development and enable users with general computer science background to develop higher quality extractors. In this demonstration 1 , we present VINERy, an intuitive yet expressive visual IDE for information extraction. We show how it supports the full cycle of IE development without requiring a single line of code and enables a wide range of users to develop high quality IE extractors with minimal efforts. The extractors visually built in VINERY are automatically translated into semantically equivalent extractors in a state-of-the-art declarative language for IE. We also demonstrate how the auto-generated extractors can then be imported into a conventional Eclipse-based IDE for further enhancement. The results of our user studies indicate that VINERY is a significant step forward in facilitating extractor development for both expert and novice IE developers.

The challenges and opportunities researchers face when working with unstructured data are hardly new. This article defines unstructured data as data that is not organized according to pre-existing schemas or structures for the sake of statistical analysis. Unstructured data poses a unique challenge for researchers focused on police and policing. The article discusses a definition of unstructured data and two of the primary challenges faced when working with such data, namely information extraction and classification problems. Two case studies are used to illuminate the challenges.

In the contemporary digital era, the exponential increase in unstructured and semi-structured data has made information extraction a cornerstone of modern data-driven research and application. The ability to transform such raw information into structured knowledge is crucial for enabling later downstream tasks. While traditional rule-based and statistical approaches to information extraction have demonstrated success in narrow, well-defined tasks, they lack the scalability and adaptability required to address the vastness and variability of present-day data. Conversely, deep neural models and especially large language models have shown remarkable capabilities in language understanding, yet they remain constrained by high computational costs and susceptibility to hallucination. <br> This thesis explores the unification of various symbolic, statistical, and neural paradigms into a cohesive hybrid framework. The central hypothesis is that by combining the strengths of data-driven representation learning with structural, rule-based, and multimodal knowledge, one can achieve information extraction systems that are more accurate, efficient, and reliable than their monolithic counterparts. To test this hypothesis, the thesis investigates a range of hybrid architectures across five key application domains. <br> In the financial domain, a hybrid contradiction detection framework integrates syntactic pre-training with transformer-based representations and clustering algorithms to identify inconsistencies within large-scale financial reports. For named entity recognition, the <em>iNERD</em> algorithm introduces rule-based constraints to guide large language models, producing syntactically valid, hallucination-free entity extractions. Thereafter, the anonymisation study leverages knowledge distillation to compress the language understanding capabilities of large decoder-only models into lightweight encoder-only architectures, enabling secure and efficient text anonymisation. In relation extraction, this work presents <em>KPI-BERT</em> and the open-source <em>KPI-EDGAR</em> dataset, combining contextual embedding models with recurrent layers and noise-based regularisation to extract key performance indicators from financial documents. Extending beyond text, the final empirical contribution introduces a multimodal dementia detection framework that fuses linguistic and acoustic representations, offering a robust approach to early, non-invasive diagnosis. <br> Together, these studies provide compelling evidence that hybrid representation learning constitutes an important paradigm for modern information extraction. This research demonstrates that hybrid systems can achieve higher precision, stronger generalisability, and improved efficiency while remaining adaptable to real-world constraints. The findings of this thesis therefore advance the field towards more trustworthy, sustainable, and application-ready artificial intelligence.

Three common approaches for deriving or predicting instantiated relations are information extraction, deductive reasoning and machine learning. Information extraction uses subsymbolic unstructured sensory information, e.g. in form of texts or images, and extracts statements using various methods ranging from simple classifiers to the most sophisticated NLP approaches. Deductive reasoning is based on a symbolic representation and derives new statements from logical axioms. Finally, machine learning can both support information extraction by deriving symbolic representations from sensory data, e.g., via classification, and can support deductive reasoning by exploiting regularities in structured data. In this paper we combine all three methods to exploit the available information in a modular way, by which we mean that each approach, i.e., information extraction, deductive reasoning, machine learning, can be optimized independently to be combined in an overall system. We validate our model using data from the YAGO2 ontology, and from Linked Life Data and Bio2RDF, all of which are part of the Linked Open Data (LOD) cloud.

Many people use the World Wide Web to get information; however, it is not always easy to obtain the desired information, since the number of Web sites and Web pages is huge, and most of them are not structured. To solve this problem, some Web site managers visualize their sites' structure and/or keyword information; this is an effective way of developing an easy-to-navigate Web site. Even if both functions are provided, however, in conventional systems they are provided as separate functions, and no relation exists between them; a user cannot see and operate a site map and keyword information as related information. Providing a site map with keywords is a new technique for visualizing and navigating Web sites. It displays both a Web site's structure and keyword information on a site map and displays the relation between them. This technique not only allows both sets of information to be visualized on the same screen, but also makes it possible to interact with one through the other: a user can interact with a Web site's structure through its keyword information, and vice versa.

The Web is populated with many Web sites containing unstructured textual information. These Web sites are a source of knowledge for various interests. As semantic annotations are only rarely used on Web sites, an automated harvesting of the knowledge without additional effort is not possible. Thus, elaborated approaches for information extraction are required. In our work we face the challenge of identifying business address data on Web sites since we see the need for this data in various applications. In order to accomplish our aim, we have developed a hybrid approach combining patterns and gazetteers obtained from freely available knowledge resources such as OpenStreetMap. Experimental evaluation on a corpus of heterogeneous Web sites shows a high recall and precision. The approach can be adapted for identification of addresses considering the different formats in various countries.

The integration of a small fraction of the information present in the Web of Documents to the Linked Data Web can provide a significant shift on the amount of information available to data consumers. However, information extracted from text does not easily fit into the usually highly normalized structure of ontology-based datasets. While the representation of structured data assumes a high level of regularity, relatively simple and consistent conceptual models, the representation of information extracted from texts need to take into account large terminological variation, complex contextual/dependency patterns, and fuzzy or conflicting semantics. This work focuses on bridging the gap between structured and unstructured data, proposing the representation of text as structured discourse graphs (SDGs), targeting an RDF representation of unstructured data. The representation focuses on a semantic best-effort information extraction scenario, where information from text is extracted under a pay-as-you-go data quality perspective, trading terminological normalization for domain-independency, context capture, wider representation scope and maximization of textual information capture.