Dissertations / Theses on the topic 'Named entity disambiguation'

Internet content has become one of the most important resources of information. Much of this information is in the form of natural language text and one of the important components of natural language text is named entities. So automatic recognition and classification of named entities has attracted researchers for many years. Named entities are mentioned in different textual forms in different documents. Also, the same textual mention may refer to different named entities. This problem is well known in NLP as a disambiguation problem. Named Entity Disambiguation (NED) refers to the task of mapping different named entity mentions in running text to their correct interpretations in a specific knowledge base (KB). NED is important for many applications like search engines and software agents that aim to aggregate information on real world entities from sources such as the Web. The main goal of this research is to develop new methods for named entity disambiguation, emphasising the importance of interdependency of named entity candidates of different textual mentions in the document. The thesis focuses on two connected problems related to disambiguation. The first is Candidates Generation, the process of finding a small set of named entity candidate entries in the knowledge base for a specific textual mention, where this set contains the correct entry in the knowledge base. The second problem is Collective Disambiguation, where all named entity textual mentions in the document are disambiguated jointly, using interdependence and semantic relations between the different NE candidates of different textual mentions. Wikipedia is used as a reference knowledge base in this research. An information retrieval framework is used to generate the named entity candidates for a textual mention. A novel document similarity function (NEBSim) based on NE co-occurrence is introduced to calculate the similarity between two documents given a specific named entity textual mention. NEB-sim is also used in conjunction with the traditional cosine similarity measure to learn a model for ranking the named entity candidates. Na\"{i}ve Bayes and SVM classifiers are used to re-rank the retrieved documents. Our experiments, carried out on TAC-KBP 2011 data, show NEBsim achieves significant improvement in accuracy as compared with a cosine similarity approach. Two novel approaches to collectively disambiguate textual mentions of named entities against Wikipedia are developed and tested using the AIDA dataset. The first represents the conditional dependencies between different named entities across Wikipedia as a Markov network, where named entities are treated as hidden variables and textual mentions as observations. The number of states and observations is huge, and na\"{i}vely using the Viterbi algorithm to find the hidden state sequence which emits the query observation sequence is computationally infeasible given a state space of this size. Based on an observation that is specific to the disambiguation problem, we develop an approach that uses a tailored approximation to reduce the size of the state space, making the Viterbi algorithm feasible. Results show good improvement in disambiguation accuracy relative to the baseline approach, and to some state-of-the-art approaches. Our approach also shows how, with suitable approximations, HMMs can be used in such large-scale state space problems. The second collective disambiguation approach uses a graph model, where all possible NE candidates are represented as nodes in the graph, and associations between different candidates are represented by edges between the nodes. Each node has an initial confidence score, e.g. entity popularity. Page-Rank is used to rank nodes, and the final rank is combined with the initial confidence for candidate selection. Experiments show the effectiveness of using Page-Rank in conjunction with initial confidence, achieving 87\% accuracy, outperforming both baseline and state-of-the-art approaches.

Publicly editable knowledge bases such as Wikipedia and Wikidata have over the years grown tremendously in size. Despite the quick growth, they can never be fully complete due to the continuous stream of events happening in the world. In the task of Entity Linking, it is attempted to link mentions of objects in a document to its respective corresponding entries in a knowledge base. However, due to the incompleteness of knowledge bases, new or emerging entities cannot be linked. Attempts to solve this issue have created the field referred to as Emerging Entities. Recent state-of-the-art work has addressed the issue with promising results in English. In this thesis, the previous work is examined by evaluating its method in the context of a much smaller language; Swedish. The results reveal an expected drop in overall performance although remaining relative competitiveness. This indicates that the method is a feasible approach to the problem of Emerging Entities even for much less used languages. Due to limitations in the scope of the related work, this thesis also suggests a method for evaluating the accuracy of how the Emerging Entities are modeled in a knowledge base. The study also provides a comprehensive look into the landscape of Emerging Entities and suggests further improvements.

The 'information explosion' has generated unprecedented amount of published information that is still growing at an astonishing rate. As the amount of information grows, the problem of managing the information becomes challenging. A key to this challenge rests on the technology of Information Extraction, which automatically transforms un-structured textual data into structured representation that can be interpreted and manipulated by machines. It is recognised that a fundamental task in Information Extraction is Named Entity Recognition, the goals of which are identifying references of named entities in unstructured documents, and classifying them into pre-defined semantic categories. Further, due to the polysemous nature of natural language, name references are often ambiguous. Resolving ambiguity concerns recognising the true referent entity of a name reference, essentially a further named entity 'recognition' step and often a compulsory process required by tasks built on top of NER. This research presents a body of work aimed at addressing three research questions for NER. The first question concerns effective and efficient methods for training data annotation, which is the task of creating essential training examples for machine learning based NER methods. The second question studies automatically generating background knowledge for NER in the form of gazetteers, which are often critical resources to improve the performance of NER methods. The third question addresses resolving ambiguous name references, a further 'recognition' step that ensures the output of NER to be usable by many complex tasks and applications. For each research question, the related literature has been carefully studied and their limitations have been identified and discussed. New hypotheses and methods have been pro-posed, leading to a number of contributions: - an approach to training data annotation for supervised NER methods, based on the study of annotator suitability and suitability based task allocation; - a method of automatically expanding existing gazetteers of pre-defined semantic categories exploiting the structure and knowledge of Wikipedia; - a method of automatically generating untyped gazetteers for NER based on the 'topic-representativeness' of words in documents; - a method of named entity disambiguation based on maximising the semantic relatedness between candidate entities in a text discourse; - a review of lexical semantic relatedness measures; and a new lexical semantic relatedness measure that harnesses knowledge from different resources. The proposed methods have been evaluated by carefully designed experiments, following the standard practice in each related research area. The results have confirmed the validity of their corresponding hypotheses, as well as the empirical effectiveness of these methods. Overall it is believed that this research has made solid contribution to the re-search of NER and related areas.

La capacità di estrarre entità da testi, collegarle tra loro ed eliminare possibili ambiguità tra di esse è uno degli obiettivi del Web Semantico. Chiamato anche Web 3.0, esso presenta numerose innovazioni volte ad arricchire il Web con dati strutturati comprensibili sia dagli umani che dai calcolatori. Nel reperimento di questi temini e nella definizione delle entities è di fondamentale importanza la loro univocità. Il nostro orizzonte di lavoro è quello delle università italiane e le entities che vogliamo estrarre, collegare e rendere univoche sono nomi di professori italiani. L’insieme di informazioni di partenza, per sua natura, vede la presenza di ambiguità. Attenendoci il più possibile alla sua semantica, abbiamo studiato questi dati ed abbiamo risolto le collisioni presenti sui nomi dei professori. Arald, la nostra architettura software per il Web Semantico, estrae entità e le collega, ma soprattutto risolve ambiguità e omonimie tra i professori delle università italiane. Per farlo si appoggia alla semantica dei loro lavori accademici e alla rete di coautori desumibile dagli articoli da loro pubblicati, rappresentati tramite un data cluster. In questo docu delle università italiane e le entities che vogliamo estrarre, collegare e rendere univoche sono nomi di professori italiani. Partendo da un insieme di informazioni che, per sua natura, vede la presenza di ambiguità, lo abbiamo studiato attenendoci il più possibile alla sua semantica, ed abbiamo risolto le collisioni che accadevano sui nomi dei professori. Arald, la nostra architettura software per il Web Semantico, estrae entità, le collega, ma soprattutto risolve ambiguità e omonimie tra i professori delle università italiane. Per farlo si appoggia alla semantica dei loro lavori accademici e alla rete di coautori desumibile dagli articoli da loro pubblicati tramite la costruzione di un data cluster.

Donner du sens aux données textuelles est une besoin essentielle pour faire les ordinateurs comprendre notre langage. Pour extraire des informations exploitables du texte, nous devons les représenter avec des descripteurs avant d’utiliser des techniques d’apprentissage. Dans ce sens, le but de cette thèse est de faire la lumière sur les représentations hétérogènes des mots et sur la façon de les exploiter tout en abordant leur nature implicitement éparse.Dans un premier temps, nous proposons un modèle de réseau basé sur des hypergraphes qui contient des données linguistiques hétérogènes dans un seul modèle unifié. En d’autres termes, nous introduisons un modèle qui représente les mots au moyen de différentes propriétés linguistiques et les relie ensemble en fonction desdites propriétés. Notre proposition diffère des autres types de réseaux linguistiques parce que nous visons à fournir une structure générale pouvant contenir plusieurstypes de caractéristiques descriptives du texte, au lieu d’une seule comme dans la plupart des représentations existantes.Cette représentation peut être utilisée pour analyser les propriétés inhérentes du langage à partir de différents points de vue, oupour être le point de départ d’un pipeline de tâches du traitement automatique de langage. Deuxièmement, nous utilisons des techniques de fusion de caractéristiques pour fournir une représentation enrichie unique qui exploite la nature hétérogènedu modèle et atténue l’eparsité de chaque représentation. Ces types de techniques sont régulièrement utilisés exclusivement pour combiner des données multimédia.Dans notre approche, nous considérons différentes représentations de texte comme des sources d’information distinctes qui peuvent être enrichies par elles-mêmes. Cette approche n’a pas été explorée auparavant, à notre connaissance. Troisièmement, nous proposons un algorithme qui exploite les caractéristiques du réseau pour identifier et grouper des mots liés sémantiquement en exploitant les propriétés des réseaux. Contrairement aux méthodes similaires qui sont également basées sur la structure du réseau, notre algorithme réduit le nombre de paramètres requis et surtout, permet l’utilisation de réseaux lexicaux ou syntaxiques pour découvrir les groupes de mots, au lieu d’un type unique des caractéristiques comme elles sont habituellement employées.Nous nous concentrons sur deux tâches différentes de traitement du langage naturel: l’induction et la désambiguïsation des sens des mots (en anglais, Word Sense, Induction and Disambiguation, ou WSI/WSD) et la reconnaissance d’entité nommées(en anglais, Named Entity Recognition, ou NER). Au total, nous testons nos propositions sur quatre ensembles de données différents. Nous effectuons nos expériences et développements en utilisant des corpus à accès libre. Les résultats obtenus nous permettent de montrer la pertinence de nos contributions et nous donnent également un aperçu des propriétés des caractéristiques hétérogènes et de leurs combinaisons avec les méthodes de fusion. Plus précisément, nos expériences sont doubles: premièrement, nous montrons qu’en utilisant des caractéristiques hétérogènes enrichies par la fusion, provenant de notre réseau linguistique proposé, nous surpassons la performance des systèmes à caractéristiques uniques et basés sur la simple concaténation de caractéristiques. Aussi, nous analysons les opérateurs de fusion utilisés afin de mieux comprendre la raison de ces améliorations. En général, l’utilisation indépendante d’opérateurs de fusion n’est pas aussi efficace que l’utilisation d’une combinaison de ceux-ci pour obtenir une représentation spatiale finale. Et deuxièmement, nous abordons encore une fois la tâche WSI/WSD, cette fois-ci avec la méthode à base de graphes proposée afin de démontrer sa pertinence par rapport à la tâche. Nous discutons les différents résultats obtenus avec des caractéristiques lexicales ou syntaxiques
Making sense of textual data is an essential requirement in order to make computers understand our language. To extract actionable information from text, we need to represent it by means of descriptors before using knowledge discovery techniques.The goal of this thesis is to shed light into heterogeneous representations of words and how to leverage them while addressing their implicit sparse nature.First, we propose a hypergraph network model that holds heterogeneous linguistic data in a single unified model. In other words, we introduce a model that represents words by means of different linguistic properties and links them together accordingto said properties. Our proposition differs to other types of linguistic networks in that we aim to provide a general structure that can hold several types of descriptive text features, instead of a single one as in most representations. This representationmay be used to analyze the inherent properties of language from different points of view, or to be the departing point of an applied NLP task pipeline. Secondly, we employ feature fusion techniques to provide a final single enriched representation that exploits the heterogeneous nature of the model and alleviates the sparseness of each representation.These types of techniques are regularly used exclusively to combine multimedia data. In our approach, we consider different text representations as distinct sources of information which can be enriched by themselves. This approach has not been explored before, to the best of our knowledge. Thirdly, we propose an algorithm that exploits the characteristics of the network to identify and group semantically related words by exploiting the real-world properties of the networks. In contrast with similar methods that are also based on the structure of the network, our algorithm reduces the number of required parameters and more importantly, allows for the use of either lexical or syntactic networks to discover said groups of words, instead of the singletype of features usually employed.We focus on two different natural language processing tasks: Word Sense Induction and Disambiguation (WSI/WSD), and Named Entity Recognition (NER). In total, we test our propositions on four different open-access datasets. The results obtained allow us to show the pertinence of our contributions and also give us some insights into the properties of heterogeneous features and their combinations with fusion methods. Specifically, our experiments are twofold: first, we show that using fusion-enriched heterogeneous features, coming from our proposed linguistic network, we outperform the performance of single features’ systems and other basic baselines. We note that using single fusion operators is not efficient compared to using a combination of them in order to obtain a final space representation. We show that the features added by each combined fusion operation are important towards the models predicting the appropriate classes. We test the enriched representations on both WSI/WSD and NER tasks. Secondly, we address the WSI/WSD task with our network-based proposed method. While based on previous work, we improve it by obtaining better overall performance and reducing the number of parameters needed. We also discuss the use of either lexical or syntactic networks to solve the task.Finally, we parse a corpus based on the English Wikipedia and then store it following the proposed network model. The parsed Wikipedia version serves as a linguistic resource to be used by other researchers. Contrary to other similar resources, insteadof just storing its part of speech tag and its dependency relations, we also take into account the constituency-tree information of each word analyzed. The hope is for this resource to be used on future developments without the need to compile suchresource from zero

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.

Open-domain question answering (QA) is an established NLP task which enables users to search for speciVc pieces of information in large collections of texts. Instead of using keyword-based queries and a standard information retrieval engine, QA systems allow the use of natural language questions and return the exact answer (or a list of plausible answers) with supporting snippets of text. In the past decade, open-domain QA research has been dominated by evaluation fora such as TREC and CLEF, where shallow techniques relying on information redundancy have achieved very good performance. However, this performance is generally limited to simple factoid and deVnition questions because the answer is usually explicitly present in the document collection. Current approaches are much less successful in Vnding implicit answers and are diXcult to adapt to more complex question types which are likely to be posed by users. In order to advance the Veld of QA, this thesis proposes a shift in focus from simple factoid questions to encyclopaedic questions: list questions composed of several constraints. These questions have more than one correct answer which usually cannot be extracted from one small snippet of text. To correctly interpret the question, systems need to combine classic knowledge-based approaches with advanced NLP techniques. To Vnd and extract answers, systems need to aggregate atomic facts from heterogeneous sources as opposed to simply relying on keyword-based similarity. Encyclopaedic questions promote QA systems which use basic reasoning, making them more robust and easier to extend with new types of constraints and new types of questions. A novel semantic architecture is proposed which represents a paradigm shift in open-domain QA system design, using semantic concepts and knowledge representation instead of words and information retrieval. The architecture consists of two phases, analysis – responsible for interpreting questions and Vnding answers, and feedback – responsible for interacting with the user. This architecture provides the basis for EQUAL, a semantic QA system developed as part of the thesis, which uses Wikipedia as a source of world knowledge and iii employs simple forms of open-domain inference to answer encyclopaedic questions. EQUAL combines the output of a syntactic parser with semantic information from Wikipedia to analyse questions. To address natural language ambiguity, the system builds several formal interpretations containing the constraints speciVed by the user and addresses each interpretation in parallel. To Vnd answers, the system then tests these constraints individually for each candidate answer, considering information from diUerent documents and/or sources. The correctness of an answer is not proved using a logical formalism, instead a conVdence-based measure is employed. This measure reWects the validation of constraints from raw natural language, automatically extracted entities, relations and available structured and semi-structured knowledge from Wikipedia and the Semantic Web. When searching for and validating answers, EQUAL uses the Wikipedia link graph to Vnd relevant information. This method achieves good precision and allows only pages of a certain type to be considered, but is aUected by the incompleteness of the existing markup targeted towards human readers. In order to address this, a semantic analysis module which disambiguates entities is developed to enrich Wikipedia articles with additional links to other pages. The module increases recall, enabling the system to rely more on the link structure of Wikipedia than on word-based similarity between pages. It also allows authoritative information from diUerent sources to be linked to the encyclopaedia, further enhancing the coverage of the system. The viability of the proposed approach was evaluated in an independent setting by participating in two competitions at CLEF 2008 and 2009. In both competitions, EQUAL outperformed standard textual QA systems as well as semi-automatic approaches. Having established a feasible way forward for the design of open-domain QA systems, future work will attempt to further improve performance to take advantage of recent advances in information extraction and knowledge representation, as well as by experimenting with formal reasoning and inferencing capabilities.

This Master's Thesis prepares Evaluation Set for Problems of Recognition and Disambiguation of Named Entities. Evaluation Set is created using Automatization and Crowdsourcing. Evaluation Set can be used in testing Edge Cases in Recognition and Disambiguation of Named Entities.

Pour les scientifiques et chercheurs, s’assurer que la connaissance est accessible pour pouvoir être réutilisée et développée est un point crucial. De plus, la façon dont nous stockons et gérons les articles scientifiques et leurs métadonnées dans les bibliothèques numériques détermine la quantité d’articles pertinents que nous pouvons découvrir et auxquels nous pouvons accéder en fonction de la signification réelle d’une requête de recherche. Cependant, sommes-nous en mesure d’explorer tous les documents scientifiques sémantiquement pertinents avec les systèmes existants de recherche d’information au moyen de mots-clés ? Il s’agit là de la question essentielle abordée dans cette thèse. L’objectif principal de nos travaux est d’élargir ou développer le spectre des connaissances des chercheurs travaillant dans un domaine interdisciplinaire lorsqu’ils utilisent les systèmes de recherche d’information des bibliothèques numériques multidisciplinaires. Le problème se pose cependant lorsque de tels chercheurs utilisent des mots-clés de recherche dépendant de la communauté dont ils sont issus alors que d’autres termes scientifiques sont attribués à des concepts pertinents lorsqu’ils sont utilisés dans des communautés de recherche différentes. Afin de proposer une solution à cette tâche d’exploration sémantique dans des bibliothèques numériques multidisciplinaires, nous avons appliqué plusieurs approches de fouille de texte. Tout d’abord, nous avons étudié la représentation sémantique des mots, des phrases, des paragraphes et des documents pour une meilleure estimation de la similarité sémantique. Ensuite, nous avons utilisé les informations sémantiques des mots dans des bases de données lexicales et des graphes de connaissance afin d’améliorer notre approche sémantique. En outre, la thèse présente quelques implémentations de cas d’utilisation du modèle que nous avons proposé
For scientists and researchers, it is very critical to ensure knowledge is accessible for re-use and development. Moreover, the way we store and manage scientific articles and their metadata in digital libraries determines the amount of relevant articles we can discover and access depending on what is actually meant in a search query. Yet, are we able to explore all semantically relevant scientific documents with the existing keyword-based search information retrieval systems? This is the primary question addressed in this thesis. Hence, the main purpose of our work is to broaden or expand the knowledge spectrum of researchers working in an interdisciplinary domain when they use the information retrieval systems of multidisciplinary digital libraries. However, the problem raises when such researchers use community-dependent search keywords while other scientific names given to relevant concepts are being used in a different research community.Towards proposing a solution to this semantic exploration task in multidisciplinary digital libraries, we applied several text mining approaches. First, we studied the semantic representation of words, sentences, paragraphs and documents for better semantic similarity estimation. In addition, we utilized the semantic information of words in lexical databases and knowledge graphs in order to enhance our semantic approach. Furthermore, the thesis presents a couple of use-case implementations of our proposed model

Information Extraction, the task of locating textual mentions of specific types of entities and their relationships, aims at representing the information contained in text documents in a structured format that is more amenable to applications in data mining, question answering, or the semantic web. The goal of our research is to design information extraction models that obtain improved performance by exploiting types of evidence that have not been explored in previous approaches. Since designing an extraction system through introspection by a domain expert is a laborious and time consuming process, the focus of this thesis will be on methods that automatically induce an extraction model by training on a dataset of manually labeled examples. Named Entity Recognition is an information extraction task that is concerned with finding textual mentions of entities that belong to a predefined set of categories. We approach this task as a phrase classification problem, in which candidate phrases from the same document are collectively classified. Global correlations between candidate entities are captured in a model built using the expressive framework of Relational Markov Networks. Additionally, we propose a novel tractable approach to phrase classification for named entity recognition based on a special Junction Tree representation. Classifying entity mentions into a predefined set of categories achieves only a partial disambiguation of the names. This is further refined in the task of Named Entity Disambiguation, where names need to be linked to their actual denotations. In our research, we use Wikipedia as a repository of named entities and propose a ranking approach to disambiguation that exploits learned correlations between words from the name context and categories from the Wikipedia taxonomy. Relation Extraction refers to finding relevant relationships between entities mentioned in text documents. Our approaches to this information extraction task differ in the type and the amount of supervision required. We first propose two relation extraction methods that are trained on documents in which sentences are manually annotated for the required relationships. In the first method, the extraction patterns correspond to sequences of words and word classes anchored at two entity names occurring in the same sentence. These are used as implicit features in a generalized subsequence kernel, with weights computed through training of Support Vector Machines. In the second approach, the implicit extraction features are focused on the shortest path between the two entities in the word-word dependency graph of the sentence. Finally, in a significant departure from previous learning approaches to relation extraction, we propose reducing the amount of required supervision to only a handful of pairs of entities known to exhibit or not exhibit the desired relationship. Each pair is associated with a bag of sentences extracted automatically from a very large corpus. We extend the subsequence kernel to handle this weaker form of supervision, and describe a method for weighting features in order to focus on those correlated with the target relation rather than with the individual entities. The resulting Multiple Instance Learning approach offers a competitive alternative to previous relation extraction methods, at a significantly reduced cost in human supervision.
text

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.