You may have to register before you can download all our books and magazines, click the sign up button below to create a free account.
This open access book introduces Vector semantics, which links the formal theory of word vectors to the cognitive theory of linguistics. The computational linguists and deep learning researchers who developed word vectors have relied primarily on the ever-increasing availability of large corpora and of computers with highly parallel GPU and TPU compute engines, and their focus is with endowing computers with natural language capabilities for practical applications such as machine translation or question answering. Cognitive linguists investigate natural language from the perspective of human cognition, the relation between language and thought, and questions about conceptual universals, rely...
Mathematical Linguistics introduces the mathematical foundations of linguistics to computer scientists, engineers, and mathematicians interested in natural language processing. The book presents linguistics as a cumulative body of knowledge from the ground up: no prior knowledge of linguistics is assumed. As the first textbook of its kind, this book is useful for those in information science and in natural language technologies.
The focus of this textbook is the meaning of linguistic expressions, typically full sentences and longer texts. The author describes the conceptual and formal tools required for building semantic systems capable of understanding text, both for specific tasks such as information extraction and question answering and for broad undertakings such as the Semantic Web. The goal here is to present the fundamental ideas that working systems rest on, and this book is aimed primarily at Computer Science or Engineering students interested in developing semantic systems. The ideal reader is a hacker, a person who delights in having an intimate understanding of the internal workings of a system.
This book constitutes the proceedings of the 12th Biennial Meeting on Mathematics in Language, MOL 12, held in Nara, Japan, in September 2011. Presented in this volume are 12 carefully selected papers, as well as the paper of the invited speaker Andreas Maletti. The papers cover such diverse topics as formal languages (string and tree transducers, grammar-independent syntactic structures, probabilistic and weighted context-free grammars, formalization of minimalist syntax), parsing and unification, lexical and compositional semantics, statistical language models, and theories of truth.
Dan Everett is a renowned linguist with an unparalleled breadth of contributions, ranging from fieldwork to linguistic theory, including phonology, morphology, syntax, semantics, sociolinguistics, psycholinguistics, historical linguistics, philosophy of language, and philosophy of linguistics. Born on the U.S. Mexican border, Daniel Everett faced much adversity growing up and was sent as a missionary to convert the Pirahã in the Amazonian jungle, a group of people who speak a language that no outsider had been able to become proficient in. Although no Pirahã person was successfully converted, Everett successfully learned and studied Pirahã, as well as multiple other languages in the Ameri...
This book constitutes the refereed proceedings of the 8th International Workshop on the Finite-State-Methods and Natural Language Processing, FSMNLP 2009. The workshop was held at the University of Pretoria, South Africa on July 2009. In total 21 papers were submitted and of those papers 13 were accepted as regular papers and a further 6 as extended abstracts. The papers are devoted to computational morphology, natural language processing, finite-state methods, automata, and related formal language theory.
This book and CD-ROM cover the breadth of contemporary finite state language modeling, from mathematical foundations to developing and debugging specific grammars.
This work, first published in 1995, is primarily addressed to phonologists interested in speech and to speech engineers interested in phonology, two groups of people with very different expectations about what constitutes a convincing, rigorous study. The subject matter, the application of autosegmental theory for Markov modeling, is technical, but not really esoteric – autosegmental theory is at the core of contemporary phonology and Markov models are the main tool of speech recognition. Therefore, it is hoped that anyone interested in at least one of these two fields will be able to follow the presentation.
Printbegrænsninger: Der kan printes 10 sider ad gangen og max. 40 sider pr. session