S
Steven Abney
Researcher at University of Michigan
Publications - 54
Citations - 7679
Steven Abney is an academic researcher from University of Michigan. The author has contributed to research in topics: Computational linguistics & Parsing. The author has an hindex of 30, co-authored 54 publications receiving 7561 citations. Previous affiliations of Steven Abney include AT&T & AT&T Labs.
Papers
More filters
Dissertation
The English Noun Phrase in its Sentential Aspect
TL;DR: Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Linguistics and Philosophy, 1987 as mentioned in this paper, Boston, Massachusetts, United States, USA.
Book ChapterDOI
Parsing By Chunks
TL;DR: The typical chunk consists of a single content word surrounded by a constellation of function words, matching a fixed template, and the relationships between chunks are mediated more by lexical selection than by rigid templates.
Journal ArticleDOI
Partial parsing via finite-state cascades
TL;DR: Deterministic parsers specified by finite state cascades may be more accurate than exhaustive search stochastic context free parsers and extended at modest cost to construct parse trees with finite feature structures.
Proceedings ArticleDOI
Procedure for quantitatively comparing the syntactic coverage of English grammars
Steven Abney,S. Flickenger,Claudia Gdaniec,C. Grishman,Philip Harrison,Donald Hindle,Robert Ingria,Frederick Jelinek,Judith L. Klavans,Mark Liberman,Mitchell Marcus,Salim Roukos,Beatrice Santorini,Tomek Strzalkowski,Ezra Black +14 more
TL;DR: The problem of quantitatively comparing the performance of different broad-coverage grammars of English has to date resisted solution as discussed by the authors, which is a problem that has been resisted solution.
Proceedings ArticleDOI
Bootstrapping
TL;DR: This paper refines the analysis of cotraining, defines and evaluates a new co-training algorithm that has theoretical justification, gives a theoretical justification for the Yarowsky algorithm, and shows that co-trained algorithms are based on different independence assumptions.