Inaug.-diss.--Breslau. / Lebenslauf. "Literaturverzeichnis": p. vii-ix.

Inaug.-Diss.--Göttingen. / Last leaf numbered p. 59. Lebenslauf. "Literatur-verzeichnis": p. v-vii.

The author's dissertation, Münich. / "Literaturverzeichnis": p. iv-x.

Thesis--Sarajevo, 1952. / At head of title: Miroslav, R. Đorđević. Includes bibliographical references.

Thesis (Ph. D.)--University of California, San Diego, 2001. / Vita. Includes bibliographical references.

No description available.

No description available.

One and the same fact in natural language can be expressed in many different ways by using different words and/or a different syntax. This phenomenon, commonly called paraphrasing, is the main reason why Natural Language Processing (NLP) is such a challenging task. This becomes especially obvious in Question Answering (QA) where the task is to automatically answer a question posed in natural language, usually in a text collection also consisting of natural language texts. It cannot be assumed that an answer sentence to a question uses the same words as the question and that these words are combined in the same way by using the same syntactic rules. In this thesis we describe methods that can help to address this problem. Firstly we explore how lexical resources, i.e. FrameNet, PropBank and VerbNet can be used to recognize a wide range of syntactic realizations that an answer sentence to a given question can have. We find that our methods based on these resources work well for web-based Question Answering. However we identify two problems: 1) All three resources as of yet have significant coverage issues. 2) These resources are not suitable to identify answer sentences that show some form of indirect evidence. While the first problem hinders performance currently, it is not a theoretical problem that renders the approach unsuitable–it rather shows that more efforts have to be made to produce more complete resources. The second problem is more persistent. Many valid answer sentences–especially in small, journalistic corpora–do not provide direct evidence for a question, rather they strongly suggest an answer without logically implying it. Semantically motivated resources like FrameNet, PropBank and VerbNet can not easily be employed to recognize such forms of indirect evidence. In order to investigate ways of dealing with indirect evidence, we used Amazon’s Mechanical Turk to collect over 8,000 manually identified answer sentences from the AQUAINT corpus to the over 1,900 TREC questions from the 2002 to 2006 QA tracks. The pairs of answer sentences and their corresponding questions form the QASP corpus, which we released to the public in April 2008. In this dissertation, we use the QASP corpus to develop an approach to QA based on matching dependency relations between answer candidates and question constituents in the answer sentences. By acquiring knowledge about syntactic and semantic transformations from dependency relations in the QASP corpus, additional answer candidates can be identified that could not be linked to the question with our first approach.

Question Time is a distinctive daily parliamentary routine. Its aim is to hold Ministers of the State accountable for the actions and decisions of the Government. However, in many Parliaments, including the New Zealand and Australian Federal Houses of Representatives, it is more of a theatrical performance where parties try their best to score political points. As any performance, Question Time is governed by certain rules and regulations outlined in an official document Standing Orders. As there is not much action, Standing Orders mainly describe language norms and specify „unparliamentary language‟. This research looks at and analyses the use of formulaic vocabulary used by MPs in the year preceding general elections in New Zealand and Australia. The formulaic language includes phrasal lexical items and formulae for asking / answering questions, for raising points of order and the Speakers‟ idiolectal phrasal vocabulary for quelling disorder in the Chambers and regulating the work of the House. The framework developed for this research consisted of the following steps: an ethnographic study of Question Time as a communicative performance which included the development of a database containing all the empirical material; a xii linguistic study of Question Time including genrelect study, parliamentary formulae study and disorder analysis before the elections. As a result this research has shown that Question Time is a communicative performance event in New Zealand and Australia with significant cultural, historic and linguistic differences in spite of the common origins of the two Parliaments. It has identified 60 Question Time genre-specific phrasal lexical items that MPs use in the two Parliaments, studied their structure and meaning (where necessary). It has also looked at the strategies the MPs employ for creating disorder in the House, and the ways of quelling disorder by the Speakers of the two Parliaments.

L'objectif de cette thèse a été de proposer une approche robuste pour traiter le problème de la recherche dela réponse précise à une question.Notre première contribution a été la conception et la mise en œuvre d'un modèle de représentation robuste de l'informationet son implémentation. Son objectif est d'apporter aux phrases des documents et aux questions de l'informationstructurelle, composée de groupes de mots typés (segments typés) et de relations entre ces groupes. Ce modèle a été évalué sur différents corpus (écrits, oraux, web) et a donné de bons résultats, prouvant sa robustesse.Notre seconde contribution a consisté en la conception d'une méthode de réordonnancement des candidats réponsesretournés par un système de questions-réponses. Cette méthode a aussi été conçue pour des besoins de robustesse, ets'appuie sur notre première contribution. L'idée est de comparer une question et le passage d'où a été extraite une réponse candidate, et de calculer un score de similarité, en s'appuyant notamment sur une distance d'édition.Le réordonnanceur a été évalué sur les données de différentes campagnes d'évaluation. Les résultats obtenus sontparticulièrement positifs sur des questions longues et complexes. Ces résultats prouvent l'intérêt de notre méthode, notreapproche étant particulièrement adaptée pour traiter les questions longues, et ce quel que soit le type de données. Leréordonnanceur a ainsi été évalué sur l'édition 2010 de la campagne d'évaluation Quaero, où les résultats sont positifs.