• Corpus ID: 16324811

Exercise Paper Information Search and Retrieval Graz University of Technology WS 2009 Common Sense Knowledge

  title={Exercise Paper Information Search and Retrieval Graz University of Technology WS 2009 Common Sense Knowledge},
  author={Christian Andrich},
This document is not a deep level resource for commonsense knowledge in computational technology, but it is an orientational overview on the subject. We will show the reasons for use of commonsense knowledge in computation science, and some methods to collect the commonsense knowledge. Furthermore, we will illustrate some practical usages of the commonsense in computational technology. 

Figures from this paper



Information retrieval with commonsense knowledge

ConceptNet is employed, which covers a rich set of commonsense concepts, to retrieve images with text descriptions by focusing on spatial relationships, to show that integrating commonsense knowledge in information retrieval is feasible.

Text Categorization with Semantic Commonsense Knowledge: First Results

This paper proposes a method for computing semantic similarity between words as a result of diffusion process in ConceptNet semantic space and presents preliminary results obtained with a novel approach that combines well established kernel text classifiers with external contextual commonsense knowledge.

ConceptNet — A Practical Commonsense Reasoning Tool-Kit

ConceptNet is a freely available commonsense knowledge base and natural-language-processing tool-kit which supports many practical textual-reasoning tasks over real-world documents including

Web-scale information extraction in knowitall: (preliminary results)

KnowItAll, a system that aims to automate the tedious process of extracting large collections of facts from the web in an autonomous, domain-independent, and scalable manner, is introduced.

A Semi-automatic Approach to Extracting Common Sense Knowledge from Knowledge Sources

An architecture for a Common Sense Knowledge Extractor is proposed that serves as an intermediary tool to extract common sense knowledge from several knowledge sources in order to develop a common sense repository.

Using NLP or NLP Resources for Information Retrieval Tasks

This chapter presents a precis of the experiments in information retrieval using NLP which have had mixed success over the last few years and introduces the respective roles of NLP and IR and summarises their early experiments on using syntactic analysis to derive term dependencies and structured representations of term-term relationships.

Method for extracting commonsense knowledge

The proposed algorithm searches automatically in Extended WordNet for all concepts that have a given property and generates axioms linking those concepts with the seed commonsense rule, and shows that using 27 commonsense rules, the algorithm generated 2596 axiomatic of which 98% were validated by human.

"All You Can Eat" Ontology-Building: Feeding Wikipedia to Cyc

This work describes methods used to add 35K new concepts mined from Wikipedia to collections in ResearchCyc entirely automatically and shows how Cyc itself can be leveraged for ontological quality control by ‘feeding’ it assertions one by one, enabling it to reject those that contradict its other knowledge.

Objects in Context

This work proposes to incorporate semantic object context as a post-processing step into any off-the-shelf object categorization model using a conditional random field (CRF) framework, which maximizes object label agreement according to contextual relevance.

Fuzzy rule encoding techniques

This paper describes three techniques for generating new rule-based knowledge by combining other precise/fuzzy rules that have relevance to database security, especially inference analysis and control.