The second release of the RASP system

Published 1 January 2006Open access

Ted Briscoe, John M. Carroll, Rebecca Watson

Citations356

TL;DR

The new release of the RASP (robust accurate statistical parsing) system, designed for syntactic annotation of free text, is described, including a revised and more semantically-motivated output representation, an enhanced grammar and part-of-speech tagger lexicon, and a more flexible and semi-supervised training method for the structural parse ranking model.

Abstract

We describe the new release of the RASP (robust accurate statistical parsing) system, designed for syntactic annotation of free text. The new version includes a revised and more semantically-motivated output representation, an enhanced grammar and part-of-speech tagger lexicon, and a more flexible and semi-supervised training method for the structural parse ranking model. We evaluate the released version on the WSJ using a relational evaluation scheme, and describe how the new release allows users to enhance performance using (in-domain) lexical information.

Keywords

Computer Science

Natural Language EngineeringApplied morphological processing of English

347 Citations2001Guido Minnen, John M. Carroll +1 more

Two newly developed computational tools for morphological processing are described: a program for analysis of English inflectional morphology, and a morphological generator, automatically derived from the analyser, which are fast, being based on finite-state techniques, and robust, in that they are able to deal effectively with unknown words.

View PDF

Robust Accurate Statistical Annotation of General Text

248 Citations2002Ted Briscoe, John A. Carroll

A robust accurate domain-independent approach to statistical parsing incorporated into the new release of the ANLT toolkit, and publicly available as a research tool.

View PDF

Does Baum-Welch re-estimation help taggers?

129 Citations1994David Elworthy

Two experiments designed to determine how much manual training information is needed for speech tagging by Hidden Markov Model suggest that initial biasing of either lexical or transition probabilities is essential to achieve a good accuracy and reveal three distinct patterns of Baum-Welch reestimation.

View PDF

A bag of useful techniques for efficient and robust parsing

69 Citations1999Bernd Kiefer, Hans‐Ulrich Krieger +2 more

New and improved techniques which help a unification-based parser to process input efficiently and robustly are described, resulting in a speed-up in parsing time of more than an order of magnitude.

View PDF

Evaluating the accuracy of an unlexicalized statistical parser on the PARC DepBank

64 Citations2006Ted Briscoe, John M. Carroll

It is demonstrated that a parser which is competitive in accuracy (without sacrificing processing speed) can be quickly tuned without reliance on large in-domain manually-constructed treebanks, making it more practical to use statistical parsers in applications that need access to aspects of predicate-argument structure.

View PDF

Ambiguity packing in constraint-based parsing: practical results

53 Citations2000Stephan Oepen, John M. Carroll

A linear-time, bidirectional subsumption test for typed feature structures is presented and it is demonstrated that (a) subsumption- and equivalence-based packing is applicable to large HPSG grammars and (b) average parse complexity can be greatly reduced in bottom-up chart parsing with comprehensive H PSG implementations.

International Workshop/Conference on Parsing TechnologiesA New Formalization of Probabilistic GLR Parsing

39 Citations1997Kentaro Unui, Virach Sornlertlamvanich +2 more

This paper presents a new formalization of probabilistic GLR language modeling for statistical parsing with a few significant refinements, while maintaining all the advantages of Briscoe and Carroll’s modeling.

CL Technical ReportsAn introduction to tag sequence grammars and the RASP system parser

26 Citations2021Ted Briscoe

This report describes the tag sequence grammars released as part of the Robust Accurate Statistical Parsing (RASP) system to help users of RASP understand the linguistic and engineering rationale behind the Grammars and prepare them to customize the system for their application.

View PDF

Efficient extraction of grammatical relations

14 Citations2005Rebecca Watson, John M. Carroll +1 more

A novel approach for applying the Inside-Outside Algorithm to a packed parse forest produced by a unification-based parser that allows a node in the forest to be assigned multiple inside and outside probabilities, enabling a set of 'weighted GRs' to be computed directly from the forest.

View PDF

Semi-supervised training of a statistical parser from unlabeled partially-bracketed data

4 Citations2007Rebecca Watson, Ted Briscoe +1 more

View PDF