Recommender systems such as Amazon, offer uses recommendations, or suggestions of items to try or buy. We propose a novel classification of reasons for including explanations in recommender systems. Our focus is on the aim of effectiveness, or decision support, and we contrast it with other metrics such as satisfaction and persuasion. In user studies, we found that people varied in the features they found important, and composed a short list of features in two domains (movies and cameras). We then built a natural language explanation testbed system, considering these features as well as the limitations of using commercial data. This testbed was used in a series of experiments to test whether personalization of explanations affects effectiveness, persuasion and satisfaction. We chose a simple form of personalization which considers likely constraints of a recommender system (e.g. limited meta-data related to the user) as well as brevity. In these experiments we found that: 1. Explanations help participants to make decisions compared to recommendations without explanations, we saw as a significant decrease in opt-outs in item ratings – participants were more likely to be able to give an initial rating for an item if they were given an explanation, and the likelihood of receiving a rating increased for feature-based explanations compared to a baseline. 2. Contrary to our initial hypothesis, our method of personalization could damage effectiveness for both movies and cameras which are domains that differ with regard to two dimensions which we found affected perceived effectiveness: cost (low vs. high), and valuation type (subjective vs. objective). 3. Participants were more satisfied with feature-based than baseline explanations. If the personalization is perceived as relevant to them, then personalized feature-based explanations were preferred over non-personalized. 4. Satisfaction with explanation was also reflected in the proportion of opt-outs. The opt-out rate for the explanations was highest in the baseline for all experiments. This was the case despite the different types of explanation baselines used in the two domains.

Syntactic parsing is one of the best understood language processing applications. Since language and grammar have been formally defined, it is easy for computers to parse the syntactic structure of natural language text. Does meaning have structure as well? If it has, how can we analyze the structure? Previous systems rely on a one-to-one correspondence between syntactic rules and semantic rules. But such systems can only be applied to limited fragments of English. In this thesis, we propose a general-purpose shallow semantic parser which utilizes a semantic network (WordNet), and a frame dataset (FrameNet). Semantic relations recognized by the parser are based on how human beings represent knowledge of the world. Parsing semantic structure allows semantic units and constituents to be accessed and processed in a more meaningful way than syntactic parsing, moving the automation of understanding natural language text to a higher level.

Abstract not available

The term “Google” has become a verb for most of us. Search engines, however, have certain limitations. For example ask it for the impact of the current global financial crisis in different parts of the world, and you can expect to sift through thousands of results for the answer. This motivates the research in complex question answering where the purpose is to create summaries of large volumes of information as answers to complex questions, rather than simply offering a listing of sources. Unlike simple questions, complex questions cannot be answered easily as they often require inferencing and synthesizing information from multiple documents. Hence, this task is accomplished by the query-focused multidocument summarization systems. In this thesis we apply different supervised learning techniques to confront the complex question answering problem. To run our experiments, we consider the DUC-2007 main task. A huge amount of labeled data is a prerequisite for supervised training. It is expensive and time consuming when humans perform the labeling task manually. Automatic labeling can be a good remedy to this problem. We employ five different automatic annotation techniques to build extracts from human abstracts using ROUGE, Basic Element (BE) overlap, syntactic similarity measure, semantic similarity measure and Extended String Subsequence Kernel (ESSK). The representative supervised methods we use are Support Vector Machines (SVM), Conditional Random Fields (CRF), Hidden Markov Models (HMM) and Maximum Entropy (MaxEnt). We annotate DUC-2006 data and use them to train our systems, whereas 25 topics of DUC-2007 data set are used as test data. The evaluation results reveal the impact of automatic labeling methods on the performance of the supervised approaches to complex question answering. We also experiment with two ensemble-based approaches that show promising results for this problem domain. / x, 108 leaves : ill. ; 29 cm

Thesis (Ph. D.)--Ohio State University, 2007. / Title from first page of PDF file. Includes bibliographical references (p. 154-163).

Thesis (Ph.D.)--University of Melbourne, Dept. of Computer Science and Software Engineering, Faculty of Engineering, 2007. / Typescript. Includes bibliographical references (leaves 171-179).

Thesis (Ph. D.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Science, Department of Systems Science and Industrial Engineering, 2008. / Includes bibliographical references.

Thesis (Ph. D.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Science, Department of Systems Science and Industrial Engineering, 2009. / Includes bibliographical references.

Thesis (Ph.D.)--Aberdeen University, 2009. / Title from web page (viewed on Feb. 23, 2010). Includes bibliographical references.

Orientadores: Ariadne Maria Brito Rizzoni Carvalho, Paul Piwek / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-08T21:38:00Z (GMT). No. of bitstreams: 1 Roman_NortonTrevisan_D.pdf: 3357998 bytes, checksum: 3ae61241e75f8f93a517ecbc678e1caf (MD5) Previous issue date: 2007 / Resumo: Esta tese apresenta várias contribuições ao campo da sumarização automática de diálogos. Ela fornece evidências em favor da hipótese de que toda vez que um diálogo apresentar um comportamento muito impolido, por um ou mais de seus interlocutores, este comportamento tenderá a ser descrito em seu resumo. Além disso, os resultados experimentais mostraram também que o relato deste comportamento é feito de modo a apresentar um forte viés, determinado pelo ponto de vista do sumarizador. Este resultado não foi afetado por restrições no tamanho do resumo. Além disso, os experimentos forneceram informações bastante úteis com relação a quando e como julgamentos de emoção e comportamento devem ser adicionados ao resumo. Para executar os experimentos, um esquema de anotação multi-dimensional e categórico foi desenvolvido, podendo ser de grande ajuda a outros pesquisadores que precisem classificar dados de maneira semelhante. Os resultados dos estudos empíricos foram usados para construir um sistema automático de sumarização de diálogos, de modo a testar sua aplicabilidade computacional. A saída do sistema consiste de resumos nos quais a informação técnica e emocional, como julgamentos do comportamento dos participantes do diálogos, são combinadas de modo a refletir o viés do sumarizador, sendo o ponto de vista definido pelo usuário / Abstract: This thesis presents a number of contributions to the field of automatic dialogue summarisation. It provides evidence for the hypothesis that whenever a dialogue features very impolite behaviour by one or more of its interlocutors, this behaviour will tend to be described in the dialogue¿s summary. Moreover, further experimental results showed that this behaviour is reported with a strong bias determined by the point of view of the summariser. This result was not affected by constraints on the summary length. The experiments provided useful information on when and how assessments of emotion and behaviour should be added to a dialogue summary. To conduct the experiments, a categorical multi-dimensional annotation scheme was developed which may also be helpful to other researchers who need to annotate data in a similar way. The results from the empirical studies were used to build an automatic dialogue summarisation system, in order to test their computational applicability. The system¿s output consists of summaries in which technical and emotional information, such as assessments of the dialogue participants¿ behaviour, are combined in a way that reflects the bias of the summariser, being the point of view defined by the user / Doutorado / Doutor em Ciência da Computação