The Second Release of the RASP System

By Ted Briscoe, John A. Carroll, Rebecca Watson. Annual Meeting of the Association for Computational Linguistics, 2006

432 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/7410c010a38e7e23f38c3c6e898d5695a4874c61

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Latent Variable Models of Selectional Preference (2010, methodology): “We trained our models on the 90-million word written component of the British National Corpus (Burnard, 1995), parsed with the RASP toolkit (Briscoe et al., 2006).”
Automatic Text Scoring Using Neural Networks (2016, methodology): “We parse the data us-ing the RASP parser (Briscoe et al., 2006) and extract a number of different features for assessing the quality of the essays.”
Unbounded Dependency Recovery for Parser Evaluation (2009, methodology): “…parsers that we chose to evaluate are the C & C CCG parser (Clark and Curran, 2007), the Enju HPSG parser (Miyao and Tsujii, 2005), the RASP parser (Briscoe et al., 2006), the Stanford parser (Klein and Manning, 2003), and the DCU post-processor of PTB parsers (Cahill et al., 2004), based on LFG…”
Vector Space Models of Lexical Meaning (2015, methodology): “The grammatical relations — expressing syntactic head-dependency relations — are from the Briscoe & Carroll (2006) scheme, and could be automatically applied using e.g. the RASP (Briscoe et al., 2006) or C&C (Clark & Curran, 2007) parsers.”
Parser Evaluation over Local and Non-Local Deep Dependencies in a Large Corpus (2011, background): “No system scored higher than 33% on the harder of the two dependencies in rnr or absol , and Stanford, MST, and RASP all scored below 25% on the harder dependency in barerel .”
Bridging semantics and syntax with graph algorithms —state-of-the-art of extracting biomedical relations (2015, methodology): “For example, the dependencies were obtained through applications of different parsers including the Pro3Gres parser [91] (Kaljurand et al. [92]), the RASP parser [93] (Vlachos et al. [94]) or both McClosky-Charniak-Johnson parser and Enju parser (Quirk et al. [95]).”
Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models (2007, methodology): “The results in Table 16 were obtained by parsing the sentences from CCGbank corresponding to those in the 560-sentence test set used by Briscoe, Carroll, and Watson (2006).”
A New Dataset and Method for Automatically Grading ESOL Texts (2011, methodology): “We parsed the training and test data (see Section 2) using the Robust Accurate Statistical Parsing (RASP) system with the standard tokenisation and sentence boundary detection modules (Briscoe et al., 2006) in order to broaden the space of candidate features suitable for the task.”
Artificial error generation for translation-based grammatical error correction (2016, methodology): “PoS tags for our data were obtained with the Robust Accurate Statistical Parser (RASP) (Briscoe et al., 2006), which uses the richer CLAWS2 tagset4 (see Appendix E).”
Bridging semantics and syntax with graph algorithms - state-of-the-art of extracting biomedical relations (2017, background): “Shared resources for biomedical relation extraction Utility category Data sources Terminology/Ontology/Knowledge Base GO [161], UMLS [58], MeSH [162], Wordnet [118], Verbnet [163], Biothesaurus [122], PDB [101], Uniprot [121], SIDER [164], DrugBank [165], HIVDB [166], RegaDB [167], Entrez Gene [153]”
Semi-Supervised Semantic Role Labeling (2009, methodology): “We obtain information about grammatical roles from the output of RASP (Briscoe et al., 2006), a broad-coverage dependency parser.”
Usage‐Based Language: Investigating the Latent Structures That Underpin Acquisition (2013, background): “Psycholinguistic research provides the evidence of usage-based acquisition in its demonstrations that language processing is exquisitely sensitive to usage frequency at all levels of language representation from phonology, through lexis and syntax, to sentence processing (Ellis, 2002).”
Linguistically Motivated Large-Scale NLP with C&C and Boxer (2007, methodology): “performance of the CCG parser with the RASP parser (Briscoe et al., 2006).”
An Unsupervised Model for Instance Level Subcategorization Acquisition (2014, methodology): “These systems extract GRs at the verb instance level from the output of a parser: the RASP general-language unlexicalized parser3 (Briscoe et al., 2006) and the lexicalized Enju parser tuned to the biomedical domain (Miyao and Tsujii, 2005),”