Laboratory Experiments in Information Retrieval, Tetsuya Sakai

Автор: Sakai, Tetsuya
Название: Laboratory experiments in information retrieval
ISBN: 9811311986 ISBN-13(EAN): 9789811311987
Издательство: Springer
Рейтинг:
Цена: 6988.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: Covering aspects from principles and limitations of statistical significance tests to topic set size design and power analysis, this book guides readers to statistically well-designed experiments. Although classical statistical significance tests are to some extent useful in information retrieval (IR) evaluation, they can harm research unless they are used appropriately with the right sample sizes and statistical power and unless the test results are reported properly. The first half of the book is mainly targeted at undergraduate students, and the second half is suitable for graduate students and researchers who regularly conduct laboratory experiments in IR, natural language processing, recommendations, and related fields.Chapters 1–5 review parametric significance tests for comparing system means, namely, t-tests and ANOVAs, and show how easily they can be conducted using Microsoft Excel or R. These chapters also discuss a few multiple comparison procedures for researchers who are interested in comparing every system pair, including a randomised version of Tukey's Honestly Significant Difference test. The chapters then deal with known limitations of classical significance testing and provide practical guidelines for reporting research results regarding comparison of means. Chapters 6 and 7 discuss statistical power. Chapter 6 introduces topic set size design to enable test collection builders to determine an appropriate number of topics to create. Readers can easily use the author’s Excel tools for topic set size design based on the paired and two-sample t-tests, one-way ANOVA, and confidence intervals. Chapter 7 describes power-analysis-based methods for determining an appropriate sample size for a new experiment based on a similar experiment done in the past, detailing how to utilize the author’s R tools for power analysis and how to interpret the results. Case studies from IR for both Excel-based topic set size design and R-based power analysis are also provided.

Автор: Dawei Song; Chin-Yew Lin; Akiko Aizawa; Kazuko Kur
Название: Information Retrieval Technology
ISBN: 3642047688 ISBN-13(EAN): 9783642047688
Издательство: Springer
Рейтинг:
Цена: 12577.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: This book constitutes the refereed proceedings of the 5th Asia Information Retrieval Symposium, AIRS 2009, held in Sapporo, Japan, in October 2009. The 18 revised full papers and 20 revised poster papers presented were carefully reviewed and selected from 82 submissions.

Автор: Jussi Karlgren; Jorma Tarhio; Heikki Hyyr?
Название: String Processing and Information Retrieval
ISBN: 3642037836 ISBN-13(EAN): 9783642037832
Издательство: Springer
Рейтинг:
Цена: 10480.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: The papers are organized in topical sections on algorithms on trees, compressed indexes, compression, indexing, content analysis, string algorithms and bioinformatics, string algorithms and theory, and using and understanding usage.

Автор: Zbigniew W. Ras; Alicja Wieczorkowska
Название: Advances in Music Information Retrieval
ISBN: 3642262716 ISBN-13(EAN): 9783642262715
Издательство: Springer
Рейтинг:
Цена: 26120.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: This book collects research performed in music information retrieval domain, and the outcomes, as well as trends in this research. Four sections cover MIR Methods and Platforms, Harmony, Music Similarity, and Content Based Identification and Retrieval.

Автор: Massimo Melucci; Ricardo Baeza-Yates
Название: Advanced Topics in Information Retrieval
ISBN: 3642268633 ISBN-13(EAN): 9783642268632
Издательство: Springer
Рейтинг:
Цена: 16070.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: In this book, the authors, selected from the lecturers of the European Summer School in Information Retrieval, illustrate key problems and topics in the current development of Information Retrieval and on future search engine technology.

Автор: Christine Urquhart
Название: Information Systems: Process and practice
ISBN: 1783302410 ISBN-13(EAN): 9781783302413
Издательство: Facet
Рейтинг:
Цена: 15312.00 р.
Наличие на складе: Нет в наличии.

Описание: This book adopts a holistic interpretation of information architecture, to offer a variety of methods, tools, and techniques that may be used when designing websites and information systems that support workflows and what people require when `managing information`.

Автор: Hang Li; Ting Liu; Wei-Ying Ma; Tetsuya Sakai; Kam
Название: Information Retrieval Technology
ISBN: 3540686339 ISBN-13(EAN): 9783540686330
Издательство: Springer
Рейтинг:
Цена: 16769.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: The papers are organized in topical sections on IR models image retrieval, text classification, chinese language processing, text processing, application of IR, machine learning, taxonomy, IR methods, information extraction, summarization, multimedia, Web IR, and text clustering.

Автор: Richard Chbeir; Youakim Badr; Ajith Abraham; Aboul
Название: Emergent Web Intelligence: Advanced Information Retrieval
ISBN: 1447125495 ISBN-13(EAN): 9781447125495
Издательство: Springer
Рейтинг:
Цена: 27251.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: This volume reviews cutting-edge technologies and insights related to XML-based and multimedia information access and data retrieval. And by applying new techniques to real-world scenarios, it details how organizations can gain competitive advantages.

Автор: Harold Thimbleby, George Buchanan, Jennifer Pearso
Название: Designing for Digital Reading
ISBN: 1627052437 ISBN-13(EAN): 9781627052436
Издательство: Mare Nostrum (Eurospan)
Рейтинг:
Цена: 6237.00 р.
Наличие на складе: Нет в наличии.

Описание: Reading is a complex human activity that has evolved, and co-evolved, with technology over thousands of years. Mass printing in the fifteenth century firmly established what we know as the modern book, with its physical format of covers and paper pages, and now-standard features such as page numbers, footnotes, and diagrams. Today, electronic documents are enabling paperless reading supported by eReading technologies such as Kindles and Nooks, yet a high proportion of users still opt to print on paper before reading. This persistent habit of ""printing to read"" is one sign of the shortcomings of digital documents -- although the popularity of eReaders is one sign of the shortcomings of paper. How do we get the best of both worlds?The physical properties of paper (for example, it is light, thin, and flexible) contribute to the ease with which physical documents are manipulated; but these properties have a completely different set of affordances to their digital equivalents. Paper can be folded, ripped, or scribbled on almost subconsciously -- activities that require significant cognitive attention in their digital form, if they are even possible. The nearly subliminal interaction that comes from years of learned behavior with paper has been described as lightweight interaction, which is achieved when a person actively reads an article in a way that is so easy and unselfconscious that they are not apt to remember their actions later.Reading is now in a period of rapid change, and digital text is fast becoming the predominant mode of reading. As a society, we are merely at the start of the journey of designing truly effective tools for handling digital text.This book investigates the advantages of paper, how the affordances of paper can be realized in digital form, and what forms best support lightweight interaction for active reading. To understand how to design for the future, we review the ways reading technology and reader behavior have both changed and remained constant over hundreds of years. We explore the reasoning behind reader behavior and introduce and evaluate several user interface designs that implement these lightweight properties familiar from our everyday use of paper.We start by looking back, reviewing the development of reading technology and the progress of research on reading over many years. Drawing key concepts from this review, we move forward to develop and test methods for creating new and more effective interactions for supporting digital reading. Finally, we lay down a set of lightweight attributes which can be used as evidence-based guidelines to improve the usability of future digital reading technologies. By the end of this book, then, we hope you will be equipped to critique the present state of digital reading, and to better design and evaluate new interaction styles and technologies.

Автор: Leif Azzopardi; Gabriella Kazai; Stephen Robertson
Название: Advances in Information Retrieval Theory
ISBN: 3642044166 ISBN-13(EAN): 9783642044168
Издательство: Springer
Рейтинг:
Цена: 12577.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: The papers are categorized into four main themes: novel IR models, evaluation, efficiency, and new perspectives in IR. Twenty-one papers fall into the general theme of novel IR models, ranging from various retrieval models, query and term selection models, Web IR models, developments in novelty and diversity, to the modeling of user aspects.

Автор: Mohand Boughanem; Catherine Berrut; Josiane Mothe;
Название: Advances in Information Retrieval
ISBN: 3642009573 ISBN-13(EAN): 9783642009570
Издательство: Springer
Рейтинг:
Цена: 18167.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: Constitutes the refereed proceedings of the 30th annual European Conference on Information Retrieval Research, ECIR 2009, held in Toulouse, France in April 2009. This book presents 42 revised full papers and 18 revised short papers with the abstracts of 3 invited lectures and 25 poster papers that were reviewed and selected from 188 submissions.