Robust Accurate Statistical Annotation of General Text

By Ted Briscoe, John A. Carroll. International Conference on Language Resources and Evaluation, 2002

329 citations recorded by the source corpus.

We describe 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. The system has been used to parse many well known corpora in order to produce data for lexical acquisition efforts; it has also been used as a component in an open-domain question answering project. The performance of the system is competitive with that of statistical parsers using highly lexicalised parse selection models. However, we plan to extend the system to improve parse coverage, depth and accuracy.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/d8fe99b6dc76dc342fe9fb47740fee40381fa13d

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

In Molecular Biology

Citations in the corpus

Characterising Measures of Lexical Distributional Similarity (2004, methodology): “The data from which sets of nearest neighbours are derived is direct-object data for 2000 nouns extracted from the BNC using a robust accurate statistical parser (RASP) (Briscoe and Carroll, 2002).”
The Second Release of the RASP System (2006, methodology): “The ﬁrst public release of the RASP system (Briscoe & Carroll, 2002) has been downloaded by over 120 sites and used in diverse natural language processing tasks, such as anaphora resolution, word sense disambiguation, identifying rhetorical relations, resolving metonymy, detecting compositionality…”
Modeling Local Coherence: An Entity-Based Approach (2005, background): “It records that trial is present in sentences 1 and 6 (as O and X respectively) but is absent from the rest of the sentences.”
Discourse Constraints for Document Compression (2010, methodology): “We obtain syntactic information in our experiments from RASP (Briscoe and Carroll 2002), a domain-independent, robust parsing system for English.”
Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models (2007, methodology): “Preiss (2003) compares the parsers of Collins and Charniak, the grammatical relations finder of Buchholz, Veenstra, and Daelemans (1999), and the Briscoe and Carroll (2002) parser, using the gold-standard grammatical relations (GRs) from Carroll, Briscoe, and Sanfilippo (1998).”
Constraint-Based Sentence Compression: An Integer Programming Approach (2006, methodology): “This is provided in our experiments by the Robust Accurate Statistical Parsing (RASP) toolkit (Briscoe and Carroll 2002).”
Composition in Distributional Models of Semantics (2010, methodology): “The latter was parsed with RASP (Briscoe & Carroll, 2002), a broad coverage syntactic analyzer.”
An Unsupervised Aspect-Sentiment Model for Online Reviews (2010, methodology): “Extracting Adjectives As a pre-processing step, we parsed our data (using RASP, Briscoe and Carroll 2002).”
Learning to Tell Tales: A Data-driven Approach to Story Generation (2009, positive): “In our experiments this knowledge base was created using the RASP relational parser (Briscoe and Carroll, 2002).”
Finding Predominant Word Senses in Untagged Text (2004, methodology): “For input we used grammatical relation data extracted using an automatic parser (Briscoe and Carroll, 2002).”
Meaningful Clustering of Senses Helps Boost Word Sense Disambiguation Performance (2006, background): “…WordNet and ODE, i.e. a function µ : Senses WN → Senses ODE ∪ { (cid:178) } , where Senses D is the set of senses in the dictionary D and (cid:178) is a special element assigned when no plausible option is available for mapping (e.g. when the ODE encodes no entry corresponding to a WordNet sense).”
Global inference for sentence compression : an integer linear programming approach (2008, methodology): “We obtain these from RASP ( Briscoe & Carroll, 2002 ), a domain-independent, robust parsing system for English.”
From distributional to semantic similarity (2004, methodology): “The Robust Accurate Statistical Parsing project (RASP) parser (Briscoe and Carroll, 2002) uses a statistical model over the possible state transitions of an underlying LR parser with a manually constructed phrase structure grammar. R ASP achieves an F-score of 76.5% on a manually annotated 500 sente”
GenERRate: Generating Errors for Use in Grammatical Error Detection (2009, methodology): “The POS-tagging is carried out by the RASP system (Briscoe and Carroll, 2002).”
UvA-DARE (Digital Academic Repository) A Dataset and Evaluation Metrics for Abstractive Compression of Sentences and Short Paragraphs (neutral): “Clarke and Lapata (2006) used the RASP parser (Briscoe and Carroll, 2002), but we expect that the Stanford parser is similarly robust and would lead to similar correlations.”
Dependency-Based Construction of Semantic Space Models (2007, methodology): “Furthermore, they used a slightly smaller corpus (only the written part of the BNC, amounting to 90% of the total corpus) and a different parser (Briscoe and Carroll 2002).”