• Publications
  • Influence
OpenRuleBench: an analysis of the performance of rule engines
TLDR
The Semantic Web initiative has led to an upsurge of the interest in rules as a general and powerful way of processing, combining, and analyzing semantic information. Expand
  • 116
  • 14
  • PDF
Logic Programming with Defaults and Argumentation Theories
TLDR
We define logic programs with defaults and argumentation theories, a new framework that unifies most of the earlier proposals for defeasible reasoning in logic programming. Expand
  • 50
  • 4
  • PDF
Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning
TLDR
We augment the Stack-LSTM transition-based AMR parser by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. Expand
  • 18
  • 3
  • PDF
Personalized Tag Recommendations via Tagging and Content-based Similarity Metrics
TLDR
This short paper describes a novel technique for generating personalized tag recommendations for users of social book- marking sites such as del.icio.us. Expand
  • 60
  • 2
  • PDF
Defeasibility in answer set programs with defaults and argumentation rules
TLDR
This work is part of the SILK (Semantic Inference on Large Knowledge) project sponsored by Vulcan Inc. Expand
  • 12
  • 1
  • PDF
Defeasibility in Answer Set Programs via Argumentation Theories
TLDR
We introduce ASPDA--a unifying framework for defeasibility of disjunctive logic programs under the Answer Set Programming (ASP). Expand
  • 4
  • 1
  • PDF
Belief Logic Programming and its Extensions ∗
Belief Logic Programming (BLP) is a novel form of quantitative logic programming in the presence of uncertain and inconsistent information, which was designed to be able to combine and correlateExpand
  • 1
  • 1
Belief Logic Programming: Uncertainty Reasoning with Correlation of Evidence
TLDR
Belief Logic Programming (BLP) is a novel form of quantitative logic programming in the presence of uncertain and inconsistent information, which was designed to be able to combine and correlate evidence obtained from non-independent information sources. Expand
  • 5
IBM Research at the CoNLL 2018 Shared Task on Multilingual Parsing
TLDR
We present a new transition-based parser, based on the Stack-LSTM framework and the ArcStandard algorithm, that handles tokenization, part-of-speech tagging, morphological tagging and dependency parsing in one single model. Expand
  • 4
  • PDF
Belief Logic Programming
  • Hui Wan
  • Computer Science
  • ICLP
  • 24 July 2009
TLDR
A less explored issue in quantitative logic programming is combining correlated pieces of information. Expand
  • 4