S YNTHESIS L ECTURES ON
H UMAN L ANGUAGE T ECHNOLOGIES
G RAEME H IRST
,Editor
Synthesis, the newdigital library of engineering and computer science (synthesis.morganclaypool.com) is an innovative information source for the professional and academic engineering and computing communities.
The basic component of the library is a 50- to 150-page self-contained electronic document that presents an important research or development topic or technique, authored by prominent contributors to the field. Called Lectures, these essay-like works offer unique value to the reader by providing more synthesis, analysis, and depth than a typical research journal article and are more modular and dynamic than traditional print and digital handbooks, contributed volumes, and monographs. Synthesis Lectures are available in three ways: in pdf format on the Synthesis Digital Library subscription web site, as individual pdf e-books, and as paperback print volumes. The library and its lectures are organized in a hierarchical structure of disciplines and series. Each series is managed by a consulting editor who oversees the selection of lecture topics and authors and peer review of the manuscripts. New series and lectures will be added continuously, making the library dynamic in a way that has not been achieved with traditional reference or educational products.
Synthesis Lectures on Human Language Technologies is edited by Graeme Hirst of the University of Toronto. The series will publish 50- to 150-page monographs on topics relating to natural language processing, computational linguistics, information retrieval, and spoken language understanding. Emphasis will be placed on important new techniques, on new applications, and on topics that combine two or more HLT subfields.
Titles in Preparation:
Dependency Parsing
Joakim Nivre, Sandra Kübler, Ryan McDonald (Fall 2008) Statistical Language Models for Information Retrieval ChengXiang Zhai (Fall 2008)
Introduction to Linguistic Annotation and Text Analytics Graham Wilcock (Fall 2008)
Spoken Dialog Systems
Kristiina Jokinen, Michael McTear (Fall 2008)
Computational Approaches to Multiword Expressions Timothy Baldwin (Winter 2009)
Semantic Role Labeling
Martha Palmer, Dan Gildea, Nianwen Xue (Winter 2009) Recognizing Textual Entailment
Ido Dagan, Dan Roth, Fabio Massimo Zanzotto (Spring 2009) Bitext Alignment
Alexander Fraser (Spring 2009)
Introduction to Arabic Natural Language Processing Nizar Habash (Summer 2009)
For the prospective author, a Synthesis lecture presents an interesting alternative to traditional print formats.
Their unique length and character make them suitable for presentations of topics that are more focused and dynamic than is appropriate for traditional monographs. Lectures can be updated often as a field evolves. A fully digital production process allows lectures to appear within weeks of their completion. Because lectures are identified by individual ISBN’s and DOI’s, are registered in the major linking databases, and are full-text indexed by major search engines and the key technical abstracting and indexing services, they will be more accessible than the typical print publication. Synthesis content is widely available through academic and corporate subscription licenses and individual lectures are sold by download and in print from the Synthesis platform and resellers such as Amazon. Authors receive a royalty on sales of individual lectures as well as a pro-rata share of subscription revenues.
Potential topics include, but are not limited to.
• Computational analysis of language
• Intelligent systems for natural language interaction
• Spoken-dialog systems
• Development and use of linguistic resources
• Statistical and machine-learning techniques for HLT
• Lexical acquisition
• Knowledge acquisition from text or speech
• Language generation and text or speech planning
• Text and speech data mining
• Information extraction and question answering from text and speech
• Summarization of text and speech
• Machine translation of speech or text
• Cross-language and multilingual information retrieval
• Multilingual speech recognition
• Spoken language understanding
• Content-based retrieval of text and spoken-language documents
• Text categorization and clustering
• Topic detection and tracking, including document routing
• Content-based filtering
• Content representation
• Content analysis, including sentiment and opinion extraction and analysis
• Language processing in adversarial contexts
• Evaluation methodologies and metrics, including user studies and task-based studies
Graeme Hirst
,Editor Michael Morgan, Publisher Professor, University of Toronto President, Morgan & Claypool
gh@cs.toronto.edu morgan@morganclaypool.comMorgan & Claypool Publishers
www.morganclaypool.com
