A simple, fast, and effective rule learner

By William W. Cohen, Yoram Singer. 1999

How researchers see this paper

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

Citations in the corpus

IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rules (2019, methodology): “Speciﬁcally, decision rule approaches such as C4.5 rules (Quinlan 1993), CN2(Clark and Niblett 1989), RIPPER (Cohen 1995), SLIP-PER (Cohen and Singer 1999) rely on heuristics, branch pruning, ad-hoc local criteria e.g., maximizing information gain, coverage, etc. because these models consider an int”
MLIC: A MaxSAT-Based Framework for Learning Interpretable Classification Rules (2018, background): “For example vaious popular decision rule approaches, such as C4.5.rules [29], CN2 [9], RIPPER [10], SLIPPER [11], all make different trade-offs in how they use these heuristic criteria for growing and pruning the rules.”
A Taxonomy of Recommender Agents on the Internet (2003, unknown): “Some examples of inductive learning techniques are Ripper (Cohen 1995b), Slipper (Cohen and Singer 1999), CN2 (Clark and Niblett 1989) and C4.5rules (Quinlan 1994).”
ENDER: a statistical framework for boosting decision rules (2010, methodology): “In SLIPPER, the optimal number of rules to be generated is determined by an internal cross-validation on the training test.”
Margin-based first-order rule learning (2007, background): “In propositional rule learning, one of the first approaches to do so was SLIPPER (Cohen and Singer 1999).”
Logistic Regression, AdaBoost and Bregman Distances (2000, methodology): “we could easily convert any system such as SLIPPER [7], BoosTexter [25] or alternating trees [15] to use logistic loss.”
The Boosting Approach to Machine Learning An Overview (2003, result): “Cohen and Singer [11] showed how to design a base learning algorithm that, when combined with AdaBoost, results in a ﬁ nal classi ﬁ er consisting of a relatively small set of rules similar to those generated by systems like RIPPER [10], IREP [36] and C4.5rules [60].”
Round Robin Classification (2002, unknown): “An evaluation of a boosting variant of Ripper (such as Slipper; Cohen and Singer, 1999) would be of interest.”
Improved Pattern Learning for Bootstrapped Entity Extraction (2014, methodology): “Other supervised systems like SRV (Freitag, 1998), SLIPPER (Cohen and Singer, 1999), (LP )2 (Ciravegna, 2001), and RAPIER (Califf and Mooney, 1999) used a fully labeled corpus to either create or score rules.”
Interpretable Random Forests via Rule Extraction (2020, background): “A large number of rule algorithms have been developed, among which the most inﬂuential Decision List (Rivest, 1987), CN2 (Clark & Niblett, 1989), C4.5 (Quinlan, 1992), IREP (Incremental Reduced Error Pruning, F¨urnkranz & Widmer, 1994), RIPPER (Repeated Incremental Pruning to Produce Error Reduction”
The effect of class distribution on classifier learning: an empirical study (2001, methodology): “These data sets include 20 data sets from the UCI repository (Blake & Merz, 1998) and 5, identified with a “+”, from previously published work by researchers at AT&T (Cohen & Singer, 1999) .”
Modeling the Detection of Textual Cyberbullying (2011, unknown): “al [7].”
A statistical approach to rule learning (2006, methodology): “Typical ensemble-based rule learning systems are SLIPPER (Cohen & Singer, 1999), LRI (Weiss & Indurkhya, 2000) and RuleFit (Friedman & Popescu, 2005).”