Design of a Multi-lingual, Parallel-processing Statistical Parsing Engine (2002)
| Venue: | In Human Language Technology Conference (HLT |
| Citations: | 36 - 1 self |
BibTeX
@INPROCEEDINGS{Bikel02designof,
author = {Daniel M. Bikel},
title = {Design of a Multi-lingual, Parallel-processing Statistical Parsing Engine},
booktitle = {In Human Language Technology Conference (HLT},
year = {2002},
pages = {24--27}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
INTRODUCTION Ever since the widespread availability of the Penn Treebank [9], there have been numerous, statistical parsers developed for English, e.g. [8, 5, 3]. To varying degrees, these parsers and others---while very successful at the tasks for which they were designed---had the following limitations: . they had a fairly fixed probabilistic structure, which could only be changed by re-coding some significant portion of the program . they had hard-coded features specific to English . they had hard-coded features specific to the Penn Treebank . they were designed only for a uniprocessor environment Building on our work in [1] and [2], we have developed a design for a head-driven, chart parsing engine that addresses all of the above limitations, and we present this design here. In particular, our design provides . appropriate layers of abstraction and encapsulation for quickly porting to di#erent languages and/or Treebank annotation styles, . has "plug-'n'-play" probabil
