Dissertations / Theses on the topic 'Named Entity Classification'

Today's communication between operators and professional drivers takes place through direct conversations between the parties. This thesis project explores the possibility to support the operators in classifying the topic of incoming communications and which entities are affected through the use of named entity recognition and topic classifications. By developing a synthetic training dataset, a NER model and a topic classification model was developed and evaluated to achieve F1-scores of 71.4 and 61.8 respectively. These results were explained by a low variance in the synthetic dataset in comparison to a transcribed dataset from the real world which included anomalies not represented in the synthetic dataset. The aforementioned models were integrated into the dialogue framework Emora to seamlessly handle the back and forth communication and generating responses.

The search for information about entities, such as people or movies, plays an increasingly important role on the Web. This information is still scattered across many Web pages, making it more time consuming for a user to find all relevant information about an entity. This thesis describes techniques to extract entities and information about these entities from the Web, such as facts, opinions, questions and answers, interactive multimedia objects, and events. The findings of this thesis are that it is possible to create a large knowledge base automatically using a manually-crafted ontology. The precision of the extracted information was found to be between 75–90 % (facts and entities respectively) after using assessment algorithms. The algorithms from this thesis can be used to create such a knowledge base, which can be used in various research fields, such as question answering, named entity recognition, and information retrieval.

Nowadays, the amount of available digital documents is rapidly growing, expanding at a considerable rate and coming from a variety of sources. Sources of unstructured and semi-structured information include the World Wide Web, news articles, biological databases, electronic mail, digital libraries, governmental digital repositories, chat rooms, online forums, blogs, and social media such as Facebook, Instagram, LinkedIn, Pinterest, Twitter, YouTube, Instagram, Pinterest, plus many others. Extracting information from these resources and finding useful information from such collections has become a challenge, which makes organizing massive amounts of data a necessity. Data mining, machine learning, and natural language processing are powerful techniques that can be used together to deal with this big challenge. Depending on the task or problem at hand, there are many different approaches that can be used. The methods that are being implemented are continuously being optimized, but not all these methods have been tested and compared for quality after training on large size corpora for supervised machine learning algorithms. The question is what happens to the quality of methods if we increase the data size from, say, 100 MB to over 1 GB? Moreover, are quality gains worth it when the rate of data processing diminishes? Can we trade quality for time efficiency and recover the quality loss by just being able to process more data? This thesis is first attempt to answer these questions in a general way for text processing tasks, as not enough research has been done to compare those methods considering the trade-offs of data size, quality, and processing time. Hence, we propose a trade-off analysis framework and apply it to three important text processing problems: Named Entity Recognition, Sentiment Analysis, and Document Classification. These problems were also chosen because they have different levels of object granularity: words, passages, and documents. For each problem, we select several machine learning algorithms and we evaluate the trade-offs of these different methods on large publicly available datasets (news, reviews, patents). We use different data subsets of increasing size ranging from 50 MB to a few GB, to explore these trade-offs. We conclude, as hypothesized, that just because the method has good performance in small data, it does not necessarily have the same performance for big data. For the two last problems, we consider similar algorithms and also consider two different data sets and two different evaluation techniques, to study the impact of the data and the evaluation technique on the resulting trade-offs. We find that the results do not change significantly.<br>Avui en dia, la quantitat de documents digitals disponibles està creixent ràpidament, expandint- se a un ritme considerable i procedint de diverses fonts. Les fonts d’informació no estructurada i semiestructurada inclouen la World Wide Web, articles de notícies, bases de dades biològiques, correus electrònics, biblioteques digitals, repositoris electrònics governamentals, , sales de xat, forums en línia, blogs i mitjans socials com Facebook, Instagram, LinkedIn, Pinterest, Twitter, YouTube i molts d’altres. Extreure’n informació d’aquests recursos i trobar informació útil d’aquestes col.leccions s’ha convertit en un desafiament que fa que l’organització d’aquesta enorme quantitat de dades esdevingui una necessitat. La mineria de dades, l’aprenentatge automàtic i el processament del llenguatge natural són tècniques poderoses que poden utilitzar-se conjuntament per fer front a aquest gran desafiament. Segons la tasca o el problema en qüestió existeixen molts emfo- caments diferents que es poden utilitzar. Els mètodes que s’estan implementant s’optimitzen continuament, però aquests mètodes d’aprenentatge automàtic supervisats han estat provats i comparats amb grans dades d’entrenament. La pregunta és : Què passa amb la qualitat dels mètodes si incrementem les dades de 100 MB a 1 GB? Més encara: Les millores en la qualitat valen la pena quan la taxa de processament de les dades minva? Podem canviar qualitat per eficiència, tot recuperant la perdua de qualitat quan processem més dades? Aquesta tesi és una primera aproximació per resoldre aquestes preguntes de forma gene- ral per a tasques de processament de text, ja que no hi ha hagut suficient investigació per a comparar aquests mètodes considerant el balanç entre el tamany de les dades, la qualitat dels resultats i el temps de processament. Per tant, proposem un marc per analitzar aquest balanç i l’apliquem a tres problemes importants de processament de text: Reconeixement d’Entitats Anomenades, Anàlisi de Sentiments i Classificació de Documents. Aquests problemes tam- bé han estat seleccionats perquè tenen nivells diferents de granularitat: paraules, opinions i documents complerts. Per a cada problema seleccionem diferents algoritmes d’aprenentatge automàtic i avaluem el balanç entre aquestes variables per als diferents algoritmes en grans conjunts de dades públiques ( notícies, opinions, patents). Utilitzem subconjunts de diferents tamanys entre 50 MB i alguns GB per a explorar aquests balanç. Per acabar, com havíem suposat, no perquè un algoritme és eficient en poques dades serà eficient en grans quantitats de dades. Per als dos últims problemes considerem algoritmes similars i també dos conjunts diferents de dades i tècniques d’avaluació per a estudiar l’impacte d’aquests dos paràmetres en els resultats. Mostrem que els resultats no canvien significativament amb aquests canvis.<br>Hoy en día, la cantidad de documentos digitales disponibles está creciendo rápidamente, ex- pandiéndose a un ritmo considerable y procediendo de una variedad de fuentes. Estas fuentes de información no estructurada y semi estructurada incluyen la World Wide Web, artículos de noticias, bases de datos biológicos, correos electrónicos, bibliotecas digitales, repositorios electrónicos gubernamentales, salas de chat, foros en línea, blogs y medios sociales como Fa- cebook, Instagram, LinkedIn, Pinterest, Twitter, YouTube, además de muchos otros. Extraer información de estos recursos y encontrar información útil de tales colecciones se ha convertido en un desafío que hace que la organización de esa enorme cantidad de datos sea una necesidad. La minería de datos, el aprendizaje automático y el procesamiento del lenguaje natural son técnicas poderosas que pueden utilizarse conjuntamente para hacer frente a este gran desafío. Dependiendo de la tarea o el problema en cuestión, hay muchos enfoques dife- rentes que se pueden utilizar. Los métodos que se están implementando se están optimizando continuamente, pero estos métodos de aprendizaje automático supervisados han sido probados y comparados con datos de entrenamiento grandes. La pregunta es ¿Qué pasa con la calidad de los métodos si incrementamos los datos de 100 MB a 1GB? Más aún, ¿las mejoras en la cali- dad valen la pena cuando la tasa de procesamiento de los datos disminuye? ¿Podemos cambiar calidad por eficiencia, recuperando la perdida de calidad cuando procesamos más datos? Esta tesis es una primera aproximación para resolver estas preguntas de forma general para tareas de procesamiento de texto, ya que no ha habido investigación suficiente para comparar estos métodos considerando el balance entre el tamaño de los datos, la calidad de los resultados y el tiempo de procesamiento. Por lo tanto, proponemos un marco para analizar este balance y lo aplicamos a tres importantes problemas de procesamiento de texto: Reconocimiento de En- tidades Nombradas, Análisis de Sentimientos y Clasificación de Documentos. Estos problemas fueron seleccionados también porque tienen distintos niveles de granularidad: palabras, opinio- nes y documentos completos. Para cada problema seleccionamos distintos algoritmos de apren- dizaje automático y evaluamos el balance entre estas variables para los distintos algoritmos en grandes conjuntos de datos públicos (noticias, opiniones, patentes). Usamos subconjuntos de distinto tamaño entre 50 MB y varios GB para explorar este balance. Para concluir, como ha- bíamos supuesto, no porque un algoritmo es eficiente en pocos datos será eficiente en grandes cantidades de datos. Para los dos últimos problemas consideramos algoritmos similares y tam- bién dos conjuntos distintos de datos y técnicas de evaluación, para estudiar el impacto de estos dos parámetros en los resultados. Mostramos que los resultados no cambian significativamente con estos cambios.

Information contained in the free text of health records is useful for the immediate care of patients as well as for medical knowledge creation. Advances in clinical language processing have made it possible to automatically extract this information, but most research has, until recently, been conducted on clinical text written in English. In this thesis, however, information extraction from Swedish clinical corpora is explored, particularly focusing on the extraction of clinical findings. Unlike most previous studies, Clinical Finding was divided into the two more granular sub-categories Finding (symptom/result of a medical examination) and Disorder (condition with an underlying pathological process). For detecting clinical findings mentioned in Swedish health record text, a machine learning model, trained on a corpus of manually annotated text, achieved results in line with the obtained inter-annotator agreement figures. The machine learning approach clearly outperformed an approach based on vocabulary mapping, showing that Swedish medical vocabularies are not extensive enough for the purpose of high-quality information extraction from clinical text. A rule and cue vocabulary-based approach was, however, successful for negation and uncertainty classification of detected clinical findings. Methods for facilitating expansion of medical vocabulary resources are particularly important for Swedish and other languages with less extensive vocabulary resources. The possibility of using distributional semantics, in the form of Random indexing, for semi-automatic vocabulary expansion of medical vocabularies was, therefore, evaluated. Distributional semantics does not require that terms or abbreviations are explicitly defined in the text, and it is, thereby, a method suitable for clinical corpora. Random indexing was shown useful for extending vocabularies with medical terms, as well as for extracting medical synonyms and abbreviation dictionaries.

Cette thèse explique et présente notre démarche de la réalisation d’un système à base de règles de reconnaissance et de classification automatique des EN en arabe. C’est un travail qui implique deux disciplines : la linguistique et l’informatique. L’outil informatique et les règles la linguistiques s’accouplent pour donner naissance à une nouvelle discipline ; celle de « traitement automatique des langues », qui opère sur des niveaux différents (morphosyntaxique, syntaxique, sémantique, syntactico-sémantique etc.). Nous avons donc, dans ce qui nous concerne, mis en œuvre des informations et règles linguistiques nécessaires au service du logiciel informatique, qui doit être en mesure de les appliquer, pour extraire et classifier, par des annotations syntaxiques et/ou sémantiques, les différentes classes d’entités nommées.Ce travail de thèse s’inscrit donc dans un cadre général de traitement automatique des langues, mais plus particulièrement dans la continuité des travaux réalisés au niveau de l’analyse morphosyntaxique par la conception et la réalisation des bases des données lexicales SAMIA et ensuite DIINAR avec l’ensemble de résultats de recherches qui en découlent. C’est une tâche qui vise à l’enrichissement lexical par des entités nommées simples et complexes, et qui veut établir la transition de l’analyse morphosyntaxique vers l’analyse syntaxique, et syntatico-sémantique dans une visée plus générale de l’analyse du contenu textuel. Pour comprendre de quoi il s’agit, il nous était important de commencer par la définition de l’entité nommée. Et pour mener à bien notre démarche, nous avons distingué entre deux types principaux : pur nom propre et EN descriptive. Nous avons aussi établi une classification référentielle en se basant sur diverses classes et sous-classes qui constituent la référence de nos annotations sémantiques. Cependant, nous avons dû faire face à deux difficultés majeures : l’ambiguïté lexicale et les frontières des entités nommées complexes. Notre système adopte une approche à base de règles syntactico-sémantiques. Il est constitué, après le Niveau 0 d’analyse morphosyntaxique, de cinq niveaux de construction de patrons syntaxiques et syntactico-sémantiques basés sur les informations linguistique nécessaires (morphosyntaxiques, syntaxiques, sémantique, et syntactico-sémantique). Ce travail, après évaluation en utilisant deux corpus, a abouti à de très bons résultats en précision, en rappel et en F–mesure. Les résultats de notre système ont un apport intéressant dans différents application du traitement automatique des langues notamment les deux tâches de recherche et d’extraction d’informations. En effet, on les a concrètement exploités dans les deux applications (recherche et extraction d’informations). En plus de cette expérience unique, nous envisageons par la suite étendre notre système à l’extraction et la classification des phrases dans lesquelles, les entités classifiées, principalement les entités nommées et les verbes, jouent respectivement le rôle d’arguments et de prédicats. Un deuxième objectif consiste à l’enrichissement des différents types de ressources lexicales à l’instar des ontologies<br>This thesis explains and presents our approach of rule-based system of arabic named entity recognition and classification. This work involves two disciplines : linguistics and computer science. Computer tools and linguistic rules are merged to give birth to a new discipline : Natural Languge Processsing, which operates in different levels (morphosyntactic, syntactic, semantic, syntactico-semantic…). So, in our particular case, we have put the necessary linguistic information and rules to software sevice. This later should be able to apply and implement them in order to recognise and classify, by syntactic and semantic annotations, the different named entity classes.This work of thesis is incorporated within the general domain of natural language processing, but it particularly falls within the scope of the continuity of the accomplished work in terms of morphosyntactic analysis and the realisation of lexical data bases of SAMIA and then DIINAR as well as the accompanying scientific recearch. This task aimes at lexical enrichement with simple and complex named entities and at establishing the transition from the morphological analysis into syntactic and syntactico-semantic analysis. The ultimate objective is text analysis. To understand what it is about, it was important to start with named entity definition. To carry out this task, we distinguished between two main named entity types : pur proper name and descriptive named entities. We have also established a referential classification on the basis of different classes and sub-classes which constitue the reference for our semantic annotations. Nevertheless, we are confronted with two major difficulties : lexical ambiguity and the frontiers of complex named entities. Our system adoptes a syntactico-semantic rule-based approach. After Level 0 of morpho-syntactic analysis, the system is made up of five levels of syntactic and syntactico-semantic patterns based on tne necessary linguisic information (i.e. morphosyntactic, syntactic, semantic and syntactico-semantic information).This work has obtained very good results in termes of precision, recall and F-measure. The output of our system has an interesting contribution in different applications of the natural language processing especially in both tasks of information retrieval and information extraction. In fact, we have concretely exploited our system output in both applications (information retrieval and information extraction). In addition to this unique experience, we envisage in the future work to extend our system into the sentence extraction and classification, in which classified entities, mainly named entities and verbs, play respectively the role of arguments and predicates. The second objective consists in the enrichment of different types of lexical resources such as ontologies

Der Großteil des geschäftsrelevanten Wissens liegt heute als unstrukturierte Information in Form von Textdaten auf Internetseiten, in Office-Dokumenten oder Foreneinträgen vor. Zur Extraktion und Verwertung dieser unstrukturierten Informationen wurde eine Vielzahl von Text-Mining-Lösungen entwickelt. Viele dieser Systeme wurden in der jüngeren Vergangenheit als Webdienste zugänglich gemacht, um die Verwertung und Integration zu vereinfachen. Die Kombination verschiedener solcher Text-Mining-Dienste zur Lösung konkreter Extraktionsaufgaben erscheint vielversprechend, da so bestehende Stärken ausgenutzt, Schwächen der Systeme minimiert werden können und die Nutzung von Text-Mining-Lösungen vereinfacht werden kann. Die vorliegende Arbeit adressiert die flexible Kombination von Text-Mining-Diensten in einem serviceorientierten System und erweitert den Stand der Technik um gezielte Methoden zur Auswahl der Text-Mining-Dienste, zur Aggregation der Ergebnisse und zur Abbildung der eingesetzten Klassifikationsschemata. Zunächst wird die derzeit existierende Dienstlandschaft analysiert und aufbauend darauf eine Ontologie zur funktionalen Beschreibung der Dienste bereitgestellt, so dass die funktionsgesteuerte Auswahl und Kombination der Text-Mining-Dienste ermöglicht wird. Des Weiteren werden am Beispiel entitätsextrahierender Dienste Algorithmen zur qualitätssteigernden Kombination von Extraktionsergebnissen erarbeitet und umfangreich evaluiert. Die Arbeit wird durch zusätzliche Abbildungs- und Integrationsprozesse ergänzt, die eine Anwendbarkeit auch in heterogenen Dienstlandschaften, bei denen unterschiedliche Klassifikationsschemata zum Einsatz kommen, gewährleisten. Zudem werden Möglichkeiten der Übertragbarkeit auf andere Text-Mining-Methoden erörtert.

Background: Most of our biomedical knowledge is only accessible through texts. The biomedical literature grows exponentially and PubMed comprises over 18.000.000 literature abstracts. Recently much effort has been put into the creation of biomedical ontologies which capture biomedical facts. The exploitation of ontologies to explore the scientific literature is a new area of research. Motivation: When people search, they have questions in mind. Answering questions in a domain requires the knowledge of the terminology of that domain. Classical search engines do not provide background knowledge for the presentation of search results. Ontology annotated structured databases allow for data-mining. The hypothesis is that ontology annotated literature databases allow for text-mining. The central problem is to associate scientific publications with ontological concepts. This is a prerequisite for ontology-based literature search. The question then is how to answer biomedical questions using ontologies and a literature corpus. Finally the task is to automate bibliometric analyses on an corpus of scientific publications. Approach: Recent joint efforts on automatically extracting information from free text showed that the applied methods are complementary. The idea is to employ the rich terminological and relational information stored in biomedical ontologies to markup biomedical text documents. Based on established semantic links between documents and ontology concepts the goal is to answer biomedical question on a corpus of documents. The entirely annotated literature corpus allows for the first time to automatically generate bibliometric analyses for ontological concepts, authors and institutions. Results: This work includes a novel annotation framework for free texts with ontological concepts. The framework allows to generate recognition patterns rules from the terminological and relational information in an ontology. Maximum entropy models can be trained to distinguish the meaning of ambiguous concept labels. The framework was used to develop a annotation pipeline for PubMed abstracts with 27,863 Gene Ontology concepts. The evaluation of the recognition performance yielded a precision of 79.9% and a recall of 72.7% improving the previously used algorithm by 25,7% f-measure. The evaluation was done on a manually created (by the original authors) curation corpus of 689 PubMed abstracts with 18,356 curations of concepts. Methods to reason over large amounts of documents with ontologies were developed. The ability to answer questions with the online system was shown on a set of biomedical question of the TREC Genomics Track 2006 benchmark. This work includes the first ontology-based, large scale, online available, up-to-date bibliometric analysis for topics in molecular biology represented by GO concepts. The automatic bibliometric analysis is in line with existing, but often out-dated, manual analyses. Outlook: A number of promising continuations starting from this work have been spun off. A freely available online search engine has a growing user community. A spin-off company was funded by the High-Tech Gründerfonds which commercializes the new ontology-based search paradigm. Several off-springs of GoPubMed including GoWeb (general web search), Go3R (search in replacement, reduction, refinement methods for animal experiments), GoGene (search in gene/protein databases) are developed.

As part of our work on the NSF funded Integrated Digital Event Archiving and Library (IDEAL) project and the Global Event and Trend Archive Research (GETAR) project, we collected over 1.4 billion tweets using over 1,000 keywords, key phrases, mentions, or hashtags, starting from 2009. Since many tweets talk about events (with useful location information), such as natural disasters, emergencies, and accidents, it is important to geo-locate those tweets whenever possible. Due to possible location ambiguity, finding a tweet's location often is challenging. Many distinct places have the same geoname, e.g., "Greenville" matches 50 different locations in the U.S.A. Frequently, in tweets, explicit location information, like geonames mentioned, is insufficient, because tweets are often brief and incomplete. They have a small fraction of the full location information of an event due to the 140 character limitation. Location indicative words (LIWs) may include latent location information, for example, "Water main break near White House" does not have any geonames but it is related to a location "1600 Pennsylvania Ave NW, Washington, DC 20500 USA" indicated by the key phrase 'White House'. To disambiguate tweet locations, we first extracted geospatial named entities (geonames) and predicted implicit state (e.g., Virginia or California) information from entities using machine learning algorithms including Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF). Implicit state information helps reduce ambiguity. We also studied how location information of events is expressed in tweets and how latent location indicative information can help to geo-locate tweets. We then used a machine learning (ML) approach to predict the implicit state using geonames and LIWs. We conducted experiments with tweets (e.g., about potholes), and found significant improvement in disambiguating tweet locations using a ML algorithm along with the Stanford NER. Adding state information predicted by our classifiers increased the possibility to find the state-level geo-location unambiguously by up to 80%. We also studied over 6 million tweets (3 mid-size and 2 big-size collections about water main breaks, sinkholes, potholes, car crashes, and car accidents), covering 17 months. We found that up to 91.1% of tweets have at least one type of location information (geo-coordinates or geonames), or LIWs. We also demonstrated that in most cases adding LIWs helps geo-locate tweets with less ambiguity using a geo-coding API. Finally, we conducted additional experiments with the five different tweet collections, and found significant improvement in disambiguating tweet locations using a ML approach with geonames and all LIWs that are present in tweet texts as features.<br>Ph. D.

O objetivo deste trabalho é desenvolver uma plataforma para anotação e classificação automática de entidades nomeadas para notícias escritas em português do Brasil. Para restringir um pouco o escopo do treinamento e análise foram utilizadas notícias esportivas do Campeonato Paulista de 2011 do portal UOL (Universo Online). O primeiro artefato desenvolvido desta plataforma foi a ferramenta WebCorpus. Esta tem como principal intuito facilitar o processo de adição de metainformações a palavras através do uso de uma interface rica web, elaborada para deixar o trabalho ágil e simples. Desta forma as entidades nomeadas das notícias são anotadas e classificadas manualmente. A base de dados foi alimentada pela ferramenta de aquisição e extração de conteúdo desenvolvida também para esta plataforma. O segundo artefato desenvolvido foi o córpus UOLCP2011 (UOL Campeonato Paulista 2011). Este córpus foi anotado e classificado manualmente através do uso da ferramenta WebCorpus utilizando sete tipos de entidades: pessoa, lugar, organização, time, campeonato, estádio e torcida. Para o desenvolvimento do motor de anotação e classificação automática de entidades nomeadas foram utilizadas três diferentes técnicas: maximização de entropia, índices invertidos e métodos de mesclagem das duas técnicas anteriores. Para cada uma destas foram executados três passos: desenvolvimento do algoritmo, treinamento utilizando técnicas de aprendizado de máquina e análise dos melhores resultados.<br>The main target of this research is to develop an automatic named entity classification tool to sport news written in Brazilian Portuguese. To reduce this scope, during training and analysis only sport news about São Paulo Championship of 2011 written by UOL2 (Universo Online) was used. The first artefact developed was the WebCorpus tool, which aims to make easier the process of add meta informations to words, through a rich web interface. Using this, all the corpora news are tagged manually. The database used by this tool was fed by the crawler tool, also developed during this research. The second artefact developed was the corpora UOLCP2011 (UOL Campeonato Paulista 2011). This corpora was manually tagged using the WebCorpus tool. During this process, seven classification concepts were used: person, place, organization, team, championship, stadium and fans. To develop the automatic named entity classification tool, three different approaches were analysed: maximum entropy, inverted index and merge tecniques using both. Each approach had three steps: algorithm development, training using machine learning tecniques and best score analysis.

碩士<br>國立交通大學<br>資訊科學系<br>91<br>Named-entity identification plays an important role in natural language processing, especially in document processing and message understanding. Named-entity can be a keyword on web or full-text retrieval. We can understand relationships among persons, events, locations, date or time in documents via correct named-entity identification. In this thesis, we use probabilities of characters used in common Chinese person names to retrieve Chinese person name. Furthermore, we propose co-occurring-neighbor word model and part-of-speech model to combine key terms and tagging information prior/posterior to named-entities. After training, we have 89% precision and 99% recall rate on Chinese person name classification experiments, 89% precision and 84% recall rate on organization classification experiments.

Digital gespeicherte Daten erfreuen sich einer stetig steigenden Verwendung. Insbesondere die computerbasierte Kommunikation über E-Mail, SMS, Messenger usw. hat klassische Kommunikationsmittel nahezu vollständig verdrängt. Einen Mehrwert aus diesen Daten zu generieren, ist sowohl im geschäftlichen als auch im privaten Bereich von entscheidender Bedeutung. Eine Möglichkeit den Nutzer zu unterstützen ist es, seine textuellen Daten umfassend zu analysieren und bestimmte Elemente hervorzuheben und ihm die Erstellung von Einträgen für Kalender, Adressbuch und dergleichen abzunehmen bzw. zumindest vorzubereiten. Eine weitere Möglichkeit stellt die semantische Suche in den Daten des Nutzers dar. Selbst mit Volltextsuche muss man bisher den genauen Wortlaut kennen, wenn man eine bestimmte Information sucht. Durch ein tiefgreifendes Verständnis für Zeit ist es nun aber möglich, über einen Zeitstrahl alle mit einem bestimmten Zeitpunkt oder einer Zeitspanne verknüpften Daten zu finden. Es existieren bereits viele Ansätze um Named Entity Recognition voll- bzw. semi-automatisch durchzuführen, aber insbesondere Verfahren, welche weitgehend sprachunabhängig arbeiten und sich somit leicht auf viele Sprachen skalieren lassen, sind kaum publiziert. Um ein solches Verfahren für natürlichsprachige Zeitausdrücke zu verbessern, werden in dieser Arbeit, basierend auf umfangreichen Analysen, Möglichkeiten vorgestellt. Es wird speziell eine Strategie entwickelt, die auf einem Verfahren des maschinellen Lernens beruht und so den manuellen Aufwand für die Unterstützung neuer Sprachen reduziert. Diese und weitere Strategien wurden implementiert und in die bestehende Architektur der Zeiterkennungsmaschine der ExB-Gruppe integriert.

Since the proposal of hypertext by Tim Berners-Lee to his employer CERN on March 12, 1989 the World Wide Web has grown to more than one billion Web pages and still grows. With the later proposed Semantic Web vision,Berners-Lee et al. suggested an extension of the existing (Document) Web to allow better reuse, sharing and understanding of data. Both the Document Web and the Web of Data (which is the current implementation of the Semantic Web) grow continuously. This is a mixed blessing, as the two forms of the Web grow concurrently and most commonly contain different pieces of information. Modern information systems must thus bridge a Semantic Gap to allow a holistic and unified access to information about a particular information independent of the representation of the data. One way to bridge the gap between the two forms of the Web is the extraction of structured data, i.e., RDF, from the growing amount of unstructured and semi-structured information (e.g., tables and XML) on the Document Web. Note, that unstructured data stands for any type of textual information like news, blogs or tweets. While extracting structured data from unstructured data allows the development of powerful information system, it requires high-quality and scalable knowledge extraction frameworks to lead to useful results. The dire need for such approaches has led to the development of a multitude of annotation frameworks and tools. However, most of these approaches are not evaluated on the same datasets or using the same measures. The resulting Evaluation Gap needs to be tackled by a concise evaluation framework to foster fine-grained and uniform evaluations of annotation tools and frameworks over any knowledge bases. Moreover, with the constant growth of data and the ongoing decentralization of knowledge, intuitive ways for non-experts to access the generated data are required. Humans adapted their search behavior to current Web data by access paradigms such as keyword search so as to retrieve high-quality results. Hence, most Web users only expect Web documents in return. However, humans think and most commonly express their information needs in their natural language rather than using keyword phrases. Answering complex information needs often requires the combination of knowledge from various, differently structured data sources. Thus, we observe an Information Gap between natural-language questions and current keyword-based search paradigms, which in addition do not make use of the available structured and unstructured data sources. Question Answering (QA) systems provide an easy and efficient way to bridge this gap by allowing to query data via natural language, thus reducing (1) a possible loss of precision and (2) potential loss of time while reformulating the search intention to transform it into a machine-readable way. Furthermore, QA systems enable answering natural language queries with concise results instead of links to verbose Web documents. Additionally, they allow as well as encourage the access to and the combination of knowledge from heterogeneous knowledge bases (KBs) within one answer. Consequently, three main research gaps are considered and addressed in this work: First, addressing the Semantic Gap between the unstructured Document Web and the Semantic Gap requires the development of scalable and accurate approaches for the extraction of structured data in RDF. This research challenge is addressed by several approaches within this thesis. This thesis presents CETUS, an approach for recognizing entity types to populate RDF KBs. Furthermore, our knowledge base-agnostic disambiguation framework AGDISTIS can efficiently detect the correct URIs for a given set of named entities. Additionally, we introduce REX, a Web-scale framework for RDF extraction from semi-structured (i.e., templated) websites which makes use of the semantics of the reference knowledge based to check the extracted data. The ongoing research on closing the Semantic Gap has already yielded a large number of annotation tools and frameworks. However, these approaches are currently still hard to compare since the published evaluation results are calculated on diverse datasets and evaluated based on different measures. On the other hand, the issue of comparability of results is not to be regarded as being intrinsic to the annotation task. Indeed, it is now well established that scientists spend between 60% and 80% of their time preparing data for experiments. Data preparation being such a tedious problem in the annotation domain is mostly due to the different formats of the gold standards as well as the different data representations across reference datasets. We tackle the resulting Evaluation Gap in two ways: First, we introduce a collection of three novel datasets, dubbed N3, to leverage the possibility of optimizing NER and NED algorithms via Linked Data and to ensure a maximal interoperability to overcome the need for corpus-specific parsers. Second, we present GERBIL, an evaluation framework for semantic entity annotation. The rationale behind our framework is to provide developers, end users and researchers with easy-to-use interfaces that allow for the agile, fine-grained and uniform evaluation of annotation tools and frameworks on multiple datasets. The decentral architecture behind the Web has led to pieces of information being distributed across data sources with varying structure. Moreover, the increasing the demand for natural-language interfaces as depicted by current mobile applications requires systems to deeply understand the underlying user information need. In conclusion, the natural language interface for asking questions requires a hybrid approach to data usage, i.e., simultaneously performing a search on full-texts and semantic knowledge bases. To close the Information Gap, this thesis presents HAWK, a novel entity search approach developed for hybrid QA based on combining structured RDF and unstructured full-text data sources.