Is the internet a suitable linguistic corpus? How can we use it in corpus techniques? What are the special properties that we need to be aware of? This book answers those questions. The Web is an exponentially increasing source of language and corpus linguistics data. From gigantic static information resources to user-generated Web 2.0 content, the breadth and depth of information available is breathtaking – and bewildering. This book explores the theory and practice of the “web as corpus”. It looks at the most common tools and methods used and features a plethora of examples based on the author's own teaching experience. This book also bridges the gap between studies in computational linguistics, which emphasize technical aspects, and studies in corpus linguistics, which focus on the implications for language theory and use.

The World Wide Web constitutes the largest existing source of texts written in a great variety of languages. A feasible and sound way of exploiting this data for linguistic research is to compile a static corpus for a given language. There are several adavantages of this approach: (i) Working with such corpora obviates the problems encountered when using Internet search engines in quantitative linguistic research (such as non-transparent ranking algorithms). (ii) Creating a corpus from web data is virtually free. (iii) The size of corpora compiled from the WWW may exceed by several orders of magnitudes the size of language resources offered elsewhere. (iv) The data is locally available to the user, and it can be linguistically post-processed and queried with the tools preferred by her/him. This book addresses the main practical tasks in the creation of web corpora up to giga-token size. Among these tasks are the sampling process (i.e., web crawling) and the usual cleanups including boilerplate removal and removal of duplicated content. Linguistic processing and problems with linguistic processing coming from the different kinds of noise in web corpora are also covered. Finally, the authors show how web corpora can be evaluated and compared to other corpora (such as traditionally compiled corpora).

Using the Web as Corpus is one of the recent challenges for corpus linguistics. This volume presents a current state-of-the-arts discussion of the topic. The articles address practical problems such as suitable linguistic search tools for accessing the www, the question of register variation, or they probe into methods for culling data from the web. The book also offers a wide range of case studies, covering morphology, syntax, lexis, as well as synchronic and diachronic variation in English. These case studies make use of the two approaches to the www in corpus linguistics - web-as-corpus and web-for-corpus-building. The case studies demonstrate that web data can provide useful additional evidence for a broad range of research questions.

WAC More and more people are using Web data for linguistic and NLP research. The Web as Corpusworkshop (WAC) provides a venue for exploring how we can use it effectively and the advancementsto which this could lead.This book is a collection of the talks presented at the 3 rd WAC in Louvain-la-Neuve (Belgium).The focus is on the description of Web corpus collection projects, the exploration of Web datacharacteristics from a linguistics/NLP perspective, and on the use of crawled Web data for NLPpurposes. CLEANEVAL Any use of Web data requires that it be cleaned in order to get rid of unwanted material including,for example, HTML markup, navigation bars, advertisements. To date there has been no sharingof resources or expertise in this particular domain and the cleaning has often been done minimally.Cleaneval was an exercise aimed at promoting collaboration and improving our understandingof the issues. Results and perspectives are presented in this book.

A linguistic corpus is a collection of texts which have been selected and brought together so that language can be studied on the computer. Today, corpus linguistics offers some of the most powerful new procedures for the analysis of language, and the impact of this dynamic and expanding sub-discipline is making itself felt in many areas of language study. In this volume, a selection of leading experts in various key areas of corpus construction offer advice in a readable and largely non-technical style to help the reader to ensure that their corpus is well designed and fit for the intended purpose. This guide is aimed at those who are at some stage of building a linguistic corpus. Little or no knowledge of corpus linguistics or computational procedures is assumed, although it is hoped that more advanced users will find the guidelines here useful. It is also aimed at those who are not building a corpus, but who need to know something about the issues involved in the design of corpora in order to choose between available resources and to help draw conclusions from their studies.

The volume “Genres on the Web” has been designed for a wide audience, from the expert to the novice. It is a required book for scholars, researchers and students who want to become acquainted with the latest theoretical, empirical and computational advances in the expanding field of web genre research. The study of web genre is an overarching and interdisciplinary novel area of research that spans from corpus linguistics, computational linguistics, NLP, and text-technology, to web mining, webometrics, social network analysis and information studies. This book gives readers a thorough grounding in the latest research on web genres and emerging document types. The book covers a wide range of web-genre focused subjects, such as: • The identification of the sources of web genres • Automatic web genre identification • The presentation of structure-oriented models • Empirical case studies One of the driving forces behind genre research is the idea of a genre-sensitive information system, which incorporates genre cues complementing the current keyword-based search and retrieval applications.

The World Wide Web constitutes the largest existing source of texts written in a great variety of languages. A feasible and sound way of exploiting this data for linguistic research is to compile a static corpus for a given language. There are several adavantages of this approach: (i) Working with such corpora obviates the problems encountered when using Internet search engines in quantitative linguistic research (such as non-transparent ranking algorithms). (ii) Creating a corpus from web data is virtually free. (iii) The size of corpora compiled from the WWW may exceed by several orders of magnitudes the size of language resources offered elsewhere. (iv) The data is locally available to the user, and it can be linguistically post-processed and queried with the tools preferred by her/him. This book addresses the main practical tasks in the creation of web corpora up to giga-token size. Among these tasks are the sampling process (i.e., web crawling) and the usual cleanups including boilerplate removal and removal of duplicated content. Linguistic processing and problems with linguistic processing coming from the different kinds of noise in web corpora are also covered. Finally, the authors show how web corpora can be evaluated and compared to other corpora (such as traditionally compiled corpora). For additional material please visit the companion website: sites.morganclaypool.com/wcc Table of Contents: Preface / Acknowledgments / Web Corpora / Data Collection / Post-Processing / Linguistic Processing / Corpus Evaluation and Comparison / Bibliography / Authors' Biographies