The vast majority of text freely available on the Internet is not available in a form that computers can understand. There have been numerous approaches to automatically extract information from human- readable sources. The most successful attempts rely on vast training sets of data. Others have succeeded in extracting restricted subsets of the available information. These approaches have limited use and require domain knowledge to be coded into the application. The current thesis proposes a novel framework for Information Extraction. From large sets of documents, the system develops statistical models of the data the user wishes to query which generally avoid the lim- itations and complexity of most Information Extractions systems. The framework uses a semi-supervised approach to minimize human input. It also eliminates the need for external Named Entity Recognition systems by relying on freely available databases. The final result is a query-answering system which extracts information from large corpora with a high degree of accuracy.

Though exploring one’s family lineage through genealogical family trees can be insightful to developing one’s identity, this knowledge is typically held behind closed doors by private companies or require expensive technologies, such as DNA testing, to uncover. With the ever-booming explosion of data on the world wide web, many unstructured text documents, both old and new, are being discovered, written, and processed which contain rich genealogical information. With access to this immense amount of data, however, entails a costly process whereby people, typically volunteers, have to read large amounts of text to find relationships between people. This delays having genealogical information be open and accessible to all. This thesis explores state-of-the-art methods for relation extraction across the genealogical and biomedical domains and bridges new and old research by proposing an updated three-tier system for parsing unstructured documents. This system makes use of recently developed and massively pretrained transformers and fine-tuning techniques to take advantage of these deep neural models’ inherent understanding of English syntax and semantics for classification. With only a fraction of labeled data typically needed to train large models, fine-tuning a LUKE relation classification model with minimal added features can identify genealogical relationships with macro precision, recall, and F1 scores of 0.880, 0.867, and 0.871, respectively, in data sets with scarce (∼10%) positive relations. Further- more, with the advent of a modern coreference resolution system utilizing SpanBERT embeddings and a modern named entity parser, our end-to-end pipeline can extract and correctly classify relationships within unstructured documents with macro precision, recall, and F1 scores of 0.794, 0.616, and 0.676, respectively. This thesis also evaluates individual components of the system and discusses future improvements to be made.

<p dir="ltr">The volume of big data has surged, notably in unstructured textual data, comprising emails, social media, and more. Currently, unstructured data represents over 80% of global data, the growth is propelled by digitalization. Unstructured text data analysis is crucial for various applications like social media sentiment analysis, customer feedback interpretation, and medical records classification. The complexity is due to the variability in language use, context sensitivity, and the nuanced meanings that are expressed in natural language. Traditional machine learning approaches, while effective in handling structured data, frequently fall short when applied to unstructured text data due to the complexities. Extracting value from this data requires advanced analytics and machine learning. Recognizing the challenges, we developed innovative ensemble approaches that combine the strengths of multiple conventional machine learning classifiers through a probabilistic approach. Response to the challenges , we developed two novel models: the Consensus-Based Integration Model (CBIM) and the Unified Predictive Averaging Model (UPAM).The CBIM and UPAM ensemble models were applied to Twitter (40,000 data samples) and the National Electronic Injury Surveillance System (NEISS) datasets (323,344 data samples) addressing various challenges in unstructured text analysis. The NEISS dataset achieved an unprecedented accuracy of 99.50%, demonstrating the effectiveness of ensemble models in extracting relevant features and making accurate predictions. The Twitter dataset, utilized for sentiment analysis, demonstrated a significant boost in accuracy over conventional approaches, achieving a maximum of 65.83%. The results highlighted the limitations of conventional machine learning approaches when dealing with complex, unstructured text data and the potential of ensemble models. The models exhibited high accuracy across various datasets and tasks, showcasing their versatility and effectiveness in obtaining valuable insights from unstructured text data. The results obtained extend the boundaries of text analysis and improve the field of natural language processing.</p>

<p>This focus of this thesis is the application of text detection, which is a field within computer vision, in structural drawings. To understand a structural system and conduct a rapid assessment of an existing structure would benefit from the ability to read the information contained within the drawing or related engineering documents. Extracting engineering data manually from the structural drawings is incredibly time-consuming and expensive. In addition, the variation in human engineers’ experience makes the output prone to errors and false evaluations. In this study, the latest development in computer vision, especially for text detection, using large volumes of words in some structural drawings, is explored and evaluated. The goal is to read text in structural drawings, which usually has some feature noises due to the high complexity of the structural annotations and lines. The dataset consists of computer-generated structural drawings which have different word shapes and types of fonts with various text orientations. The utilized structural drawings are floor plans, and thus contain structural details which are filled with various structural element labels and dimensions. Fine tuning of the pre-trained model yieldssignificant performance in unstructured text detection, especially in the model’s recall. The results demonstrate that the developed predictive modeling workflow and its computational requirements are sufficient for the unstructured text detection in structural drawings </p>

Financial fraud rampages onwards seemingly uncontained. The annual cost of fraud in the UK is estimated to be as high as £193bn a year [1] . From a data science perspective and hitherto less explored this thesis demonstrates how the use of linguistic features to drive data mining algorithms can aid in unravelling fraud. To this end, the spotlight is turned on Financial Statement Fraud (FSF), known to be the costliest type of fraud [2]. A new corpus of 6.3 million words is composed of102 annual reports/10-K (narrative sections) from firms formally indicted for FSF juxtaposed with 306 non-fraud firms of similar size and industrial grouping. Differently from other similar studies, this thesis uniquely takes a wide angled view and extracts a range of features of different categories from the corpus. These linguistic correlates of deception are uncovered using a variety of techniques and tools. Corpus linguistics methodology is applied to extract keywords and to examine linguistic structure. N-grams are extracted to draw out collocations. Readability measurement in financial text is advanced through the extraction of new indices that probe the text at a deeper level. Cognitive and perceptual processes are also picked out. Tone, intention and liquidity are gauged using customised word lists. Linguistic ratios are derived from grammatical constructs and word categories. An attempt is also made to determine ‘what’ was said as opposed to ‘how’. Further a new module is developed to condense synonyms into concepts. Lastly frequency counts from keywords unearthed from a previous content analysis study on financial narrative are also used. These features are then used to drive machine learning based classification and clustering algorithms to determine if they aid in discriminating a fraud from a non-fraud firm. The results derived from the battery of models built typically exceed classification accuracy of 70%. The above process is amalgamated into a framework. The process outlined, driven by empirical data demonstrates in a practical way how linguistic analysis could aid in fraud detection and also constitutes a unique contribution made to deception detection studies.