People interact with each other through natural language to express feelings, thoughts, intentions, instructions etc. These interactions as a result form relationships. Besides names of relationships like siblings, spouse, friends etc., a number of dimensions (e.g. cooperative vs. competitive, temporary vs. enduring, equal vs. hierarchical etc.) can also be used to capture the underlying properties of interpersonal interactions and relationships. More fine-grained descriptors (e.g. angry, rude, nice, supportive etc.) can also be used to indicate the reasons or social-acts behind the dimension cooperative vs. competitive. The way people interact with others may also tell us about their personal traits, which in turn may be indicative of their probable success in their future. The works presented in the dissertation involve creating corpora with fine-grained descriptors of interactions and relationships. We also described experiments and their results that indicated that the processes of identifying the dimensions can be automated.

MEDLINE, a large and constantly increasing collection of biomedical article references, has been the source of numerous investigations related to textual information retrieval and knowledge capture, including article categorization, bibliometric analysis, semantic query answering, and biological concept recognition and relationship extraction. This dissertation discusses the design and development of novel methods that contribute to the tasks of document categorization and relationship extraction. The two investigations result in a fast tool for building descriptive models capable of categorizing documents to multiple labels and a highly effective method able to extract broad range of relationships between entities embedded in text. Additionally, an application that aims at representing the extracted knowledge in a strictly defined but highly expressive structure of ontology is presented. The classification of documents is based on an idea of building association rules that consist of frequent patterns of words appearing in documents and classes these patterns are likely to be assigned to. The process of building the models is based on a tree enumeration technique and dataset projection. The resulting algorithm offers two different tree traversing strategies, breadth-first and depth-first. The classification scenario involves the use of two alternative thresholding strategies based on either the document-independent confidence of the rules or a similarity measure between a rule and a document. The presented classification tool is shown to perform faster than other methods and is the first associative-classification solution to incorporate multiple classes and the information about recurrence of words in documents. The extraction of relations between entities embedded in text involves the utilization of the output of a constituent parser and a set of manually developed tree-like patterns. Both serve as the input of a novel algorithm that solves the newly formulated problem of constrained constituent tree inclusion with regular expression matching. The proposed relation extraction method is demonstrated to be parser-independent and outperforms in terms of effectiveness dependency-parser-based and machine-learning-based solutions. The extracted knowledge is further embedded in an existing ontology, which together with the structure-driven modification of the ontology results in a comprehensible, inference-consistent knowledge base constituting a tangible representation of knowledge and a potential component of applications such as semantically enhanced query answering systems.

No description available.

This master thesis deals with the extraction of relationships between named entities in the text. In the theoretical part of the thesis, the issue of natural language representation for machine processing is discussed. Subsequently, two partial tasks of relationship extraction are defined, namely named entities recognition and classification of relationships between them, including a summary of state-of-the-art solutions. In the practical part of the thesis, system for automatic extraction of relationships between named entities from downloaded pages is designed. The classification of relationships between entities is based on the pre-trained transformers. In this thesis, four pre-trained transformers are compared, namely BERT, XLNet, RoBERTa and ALBERT.

Many organizations have realized that the growing amount of unstructured text may contain information that can be used for different purposes, such as making decisions. Organizations can by using so-called text mining tools, extract information from text documents. For example within military and intelligence activities it is important to go through reports and look for entities such as names of people, events, and the relationships in-between them when criminal or other interesting activities are being investigated and mapped. This study explores how information quality can be measured and what challenges it involves. It is done on the basis of Wang and Strong (1996) theory about how information quality can be measured. The theory is tested and discussed from empirical material that contains interviews from two case organizations. The study observed two important aspects to take into consideration when measuring information quality: context dependency and source criticism. Context dependency means that the context in which information quality should be measured in must be defined based on the consumer’s needs. Source criticism implies that it is important to take the original source into consideration, and how reliable it is. Further, data quality and information quality is often used interchangeably, which means that organizations needs to decide what they really want to measure. One of the major challenges in developing software for entity extraction is that the system needs to understand the structure of natural language, which is very complicated. / Många organisationer har insett att den växande mängden ostrukturerad text kan innehålla information som kan användas till flera ändamål såsom beslutsfattande. Genom att använda så kallade text-mining verktyg kan organisationer extrahera information från textdokument. Inom till exempel militär verksamhet och underrättelsetjänst är det viktigt att kunna gå igenom rapporter och leta efter exempelvis namn på personer, händelser och relationerna mellan dessa när brottslig eller annan intressant verksamhet undersöks och kartläggs. I studien undersöks hur informationskvalitet kan mätas och vilka utmaningar det medför. Det görs med utgångspunkt i Wang och Strongs (1996) teori om hur informationskvalité kan mätas. Teorin testas och diskuteras utifrån ett empiriskt material som består av intervjuer från två fall-organisationer. Studien uppmärksammar två viktiga aspekter att ta hänsyn till för att mäta informationskvalitét; kontextberoende och källkritik. Kontextberoendet innebär att det sammanhang inom vilket informationskvalitét mäts måste definieras utifrån konsumentens behov. Källkritik innebär att det är viktigt att ta hänsyn informationens ursprungliga källa och hur trovärdig den är. Vidare är det viktigt att organisationer bestämmer om det är data eller informationskvalitét som ska mätas eftersom dessa två begrepp ofta blandas ihop. En av de stora utmaningarna med att utveckla mjukvaror för entitetsextrahering är att systemen ska förstå uppbyggnaden av det naturliga språket, vilket är väldigt komplicerat.

Relationship extraction is the task of extracting semantic relationships between en- tities from a text. We create a Czech Relationship Extraction Dataset (CERED) using distant supervision on Wikidata and Czech Wikipedia. We detail the methodology we used and the pitfalls we encountered. Then we use CERED to fine-tune a neural network model for relationship extraction. We base our model on BERT - a linguistic model pre-trained on extensive unlabeled data. We demonstrate that our model performs well on existing English relationship datasets (Semeval 2010 Task 8, TACRED) and report the results we achieved on CERED. 1

Das Finden von zuverlässigen Informationen über gegebene Ereignisse aus großen und dynamischen Textsammlungen, wie dem Web, ist ein wichtiges Thema. Zum Beispiel sind Rettungsteams und Versicherungsunternehmen an prägnanten Fakten über Schäden nach Katastrophen interessiert, die heutzutage online in Web-Blogs, Zeitungsartikeln, Social Media etc. zu finden sind. Solche Fakten helfen, die erforderlichen Hilfsmaßnahmen zu bestimmen und unterstützen deren Koordination. Allerdings ist das Finden, Extrahieren und Aggregieren nützlicher Informationen ein hochkomplexes Unterfangen: Es erfordert die Ermittlung geeigneter Textquellen und deren zeitliche Einordung, die Extraktion relevanter Fakten in diesen Texten und deren Aggregation zu einer verdichteten Sicht auf die Ereignisse, trotz Inkonsistenzen, vagen Angaben und Veränderungen über die Zeit. In dieser Arbeit präsentieren und evaluieren wir Techniken und Lösungen für jedes dieser Probleme, eingebettet in ein vierstufiges Framework. Die angewandten Methoden beruhen auf Verfahren des Musterabgleichs, der Verarbeitung natürlicher Sprache und des maschinellen Lernens. Zusätzlich berichten wir über die Ergebnisse zweier Fallstudien, basierend auf dem Einsatz des gesamten Frameworks: Die Ermittlung von Daten über Erdbeben und Überschwemmungen aus Webdokumenten. Unsere Ergebnisse zeigen, dass es unter bestimmten Umständen möglich ist, automatisch zuverlässige und zeitgerechte Daten aus dem Internet zu erhalten. / Finding reliable information about given events from large and dynamic text collections, such as the web, is a topic of great interest. For instance, rescue teams and insurance companies are interested in concise facts about damages after disasters, which can be found today in web blogs, online newspaper articles, social media, etc. Knowing these facts helps to determine the required scale of relief operations and supports their coordination. However, finding, extracting, and condensing specific facts is a highly complex undertaking: It requires identifying appropriate textual sources and their temporal alignment, recognizing relevant facts within these texts, and aggregating extracted facts into a condensed answer despite inconsistencies, uncertainty, and changes over time. In this thesis, we present and evaluate techniques and solutions for each of these problems, embedded in a four-step framework. Applied methods are pattern matching, natural language processing, and machine learning. We also report the results for two case studies applying our entire framework: gathering data on earthquakes and floods from web documents. Our results show that it is, under certain circumstances, possible to automatically obtain reliable and timely data from the web.