Finite-State Text Processing

Erscheinungsjahr 2021
ISBN: 978-3-031-01051-4
Verlag: Springer International Publishing

Buch, Englisch, 140 Seiten, Format (B × H): 191 mm x 235 mm, Gewicht: 312 g

Reihe: Synthesis Lectures on Human Language Technologies

Weighted finite-state transducers (WFSTs) are commonly used by engineers and computational linguists for processing and generating speech and text. This book first provides a detailed introduction to this formalism. It then introduces Pynini, a Python library for compiling finite-state grammars and for combining, optimizing, applying, and searching finite-state transducers. This book illustrates this library's conventions and use with a series of case studies. These include the compilation and application of context-dependent rewrite rules, the construction of morphological analyzers and generators, and text generation and processing applications.

Zielgruppe

Professional/practitioner

Autoren/Hrsg.

Sproat, Richard

Gorman, Kyle

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Spracherkennung, Sprachverarbeitung
• Geisteswissenschaften Sprachwissenschaft Computerlinguistik, Korpuslinguistik

Inhaltsverzeichnis

Preface.- Acknowledgments.- Finite-State Machines.- The Pynini Library.- Basic Algorithms.- Advanced Algorithms.- Rewrite Rules.- Morphological Analysis and Generation.- The Future.- Bibliography.- Authors' Biographies.- Index.

Über Autor(innen)

Kyle Gorman is an assistant professor of linguistics at the Graduate Center, City University of New York, where he directs the master’s program in computational linguistics; he also works as a software engineer at Google. He was previously an assistant professor at the Oregon Health & Science University in Portland. He holds a Ph.D. in linguistics from the University of Pennsylvania. His research interests include phonology, morphology, and speech and text processing. He is a maintainer of the OpenFst and OpenGrm libraries and the creator of Pynini. He lives in Brooklyn.Richard Sproat received his Ph.D. in linguistics from the Massachusetts Institute of Technology in 1985. Since then, he has worked in a number of areas of linguistics and computational linguistics, but he is perhaps best known for his work on text normalization for speech applications such as text-to-speech synthesis. His recent interests include neural text processing, finite-state methods, and computational modelsof writing systems. He is currently a research scientist at Google in Tokyo.