Dependency-Based Evaluation of Minipar

By Dekang Lin. 2003

783 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/99328d4b34d1ac02252258a9437b8b2c1acdb92c

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

Extracting Product Features and Opinions from Reviews (2005, methodology): “This idea is similar to that of (Kim and Hovy, 2004) and (Hu and Liu, 2004), but instead of using a window of size k or the output of a noun phrase chunker, OPINE takes advantage of the syntactic dependencies computed by the MINIPAR parser.”
CCGbank: A Corpus of CCG Derivations and Dependency Structures Extracted from the Penn Treebank (2007, background): “In our running example, the root is S [ dcl ] , because its Treebank label is S , and its head word, the auxiliary, has the POS tag VBZ .”
Learning Entailment Relations by Global Graph Structure Optimization (2012, methodology): “A health-care corpus of 632MB was harvested from the Web and parsed using the Mini-par parser (Lin 1998b).”
Generating Typed Dependency Parses from Phrase Structure Parses (2006, background): “Minipar is confused by punctuation (this fact has already be mentioned in (Lin, 1998)): e.”
Examining the Role of Linguistic Knowledge Sources in the Automatic Identification and Classification of Reviews (2006, methodology): “15 As we can see, the baseline achieves an accuracy of 87.1% and 82.7% on Datasets A and B, respectively. Note that our result on Dataset A is as strong as that obtained by Pang and Lee (2004) via their subjectivity summarization algo-”
Automatic Multi-Layer Corpus Annotation for Evaluation Question Answering Methods: CBC4Kids (2003, background): “Minipar (Lin, 1998) is a rule-based parser that implements a procedural model of Government & Binding (GB) realized as message passing; it is derived from Principar (Lin, 1995), incorporates knowledge about named entities and comprises a lexicon 90k lemmata.”
Structured Relation Discovery using Generative Models (2011, methodology): “The baseline classifier employs features that Mintz et al. (2009) used.”
Distant supervision for relation extraction without labeled data (2009, methodology): “In order to generate these features we parse each sentence with the broad-coverage dependency parser MINIPAR (Lin, 1998).”
Extracting and Ranking Product Features in Opinion Documents (2010, background): “These relations can be identified via a dependency parser (Lin, 1998) based on the dependency grammar.”
A Context-Theoretic Framework for Compositionality in Distributional Semantics (2011, background): “Approaches to the task of recognizing textual entailment, including the use of subsequence matching, lexical entailment probability, and latent Dirichlet allocation, can be described within our framework.”
Using the Web to Obtain Frequencies for Unseen Bigrams (2003, methodology): “Lin (1998) evaluated the parser on the susanne corpus (Sampson, 1995), a domain independent corpus of British English, and achieved a recall of 79% and precision of 89% on the dependency relations.”
Semantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition (2007, methodology): “(iii) Dependency parsing, using Minipar (Lin, 1998b).”
A Confidence Model for Syntactically-Motivated Entailment Proofs (2011, methodology): “We used the Minipar parser (Lin, 1998b) (5)We used Stanford NE recognizer (Finkel et al.”
Semantic Taxonomy Induction from Heterogenous Evidence (2006, methodology): “The features used for predicting the hypernym relationship are obtained by parsing a large corpus of newswire and encyclopedia text with MINIPAR (Lin, 1998).”
The Stanford Typed Dependencies Representation (2008, methodology): “Second, we noted the widespread use of Mini-Par (Lin, 1998) and the Link Parser (Sleator and Temperley, 1993).”
Bootstrapping Path-Based Pronoun Resolution (2006, methodology): “Also, we use Minipar’s named-entity recognition to replace named-entity nouns by the semantic category of their named-entity, when available.”
Robust Accurate Statistical Annotation of General Text (2002, methodology): “Similar relation-based schemes have been employed by others (e.g. Lin, 1998; Collins, 1999; Srinivas, 2000).”