Accurate Context-Aware Search for Managed Document Collections. Search is a key component of a vast range of computing applications. However, while search on large collections of general-purpose text is well-understood, and the best systems are highly effective, search on smaller or special-purpose collections is much less reliable and has attracted relatively little research. By identifying general ways of using context such as user history or prior page usefulness, the quality of search in s ....Accurate Context-Aware Search for Managed Document Collections. Search is a key component of a vast range of computing applications. However, while search on large collections of general-purpose text is well-understood, and the best systems are highly effective, search on smaller or special-purpose collections is much less reliable and has attracted relatively little research. By identifying general ways of using context such as user history or prior page usefulness, the quality of search in such cases can be greatly improved. Products that make use of these principles will provide greater workplace efficiency and be able to locate information that other search tools cannot identify.Read moreRead less
Special Research Initiatives - Grant ID: SR0567319
Funder
Australian Research Council
Funding Amount
$145,000.00
Summary
DADA-HCS: Distributed Access and Data Annotation for the Human Communication Sciences. This project aims to build a National storage network for human
communication sciences data which will enable subscribers to
publish their own data and make use of data provided by other subscribers or third party suppliers. The network will provide infrastructure for rights management of data, in particular making sure that any original conditions on the collection and publication of data are respected. T ....DADA-HCS: Distributed Access and Data Annotation for the Human Communication Sciences. This project aims to build a National storage network for human
communication sciences data which will enable subscribers to
publish their own data and make use of data provided by other subscribers or third party suppliers. The network will provide infrastructure for rights management of data, in particular making sure that any original conditions on the collection and publication of data are respected. The project will support collaborative annotation of data stored in the network so its use can be maximised across disciplines.
Read moreRead less
Using Past Queries for Fast and Accurate Web Searching. Searching the entire Internet, or a company web site, has become a vital task for modern organisations. While there has been significant research into improving search engines through using web pages themselves, very little attention has been paid to improving web search by exploiting the vast numbers of queries that users submit to search engines each day. This project will use state of the art compression and algorithmic techniques to imp ....Using Past Queries for Fast and Accurate Web Searching. Searching the entire Internet, or a company web site, has become a vital task for modern organisations. While there has been significant research into improving search engines through using web pages themselves, very little attention has been paid to improving web search by exploiting the vast numbers of queries that users submit to search engines each day. This project will use state of the art compression and algorithmic techniques to improve the speed and accuracy of web search using data gleaned from millions of Internet queries (provided under agreement by Microsoft). Improving search engines will have a direct benefit to many Australian industries, and support the government's priority area of "smart information use".Read moreRead less
The Quantum Mechanics of Semantic Space. Quantum mechanics (QM) is a well known and successful theory from physics which has recently attracted quite some public interest. Quantum Mechanics is emerging out of physics and permeating into other areas, for example, information retrieval, human language and cognition. This offers tantalizing possibilities and bizarre implications, some of which, if realized, can lead to genuine breakthroughs in producing information technology to enhance human aware ....The Quantum Mechanics of Semantic Space. Quantum mechanics (QM) is a well known and successful theory from physics which has recently attracted quite some public interest. Quantum Mechanics is emerging out of physics and permeating into other areas, for example, information retrieval, human language and cognition. This offers tantalizing possibilities and bizarre implications, some of which, if realized, can lead to genuine breakthroughs in producing information technology to enhance human awareness in increasingly complex information environments. Through this project, Australia has the possibility to be at the forefront and have a hand in determining such developments.Read moreRead less
A scheme of local compilation of mobile collectors for image and video search engines. The object collector is an important component in a Web search engine. A collector collects Web objects (text, image, video, etc), extracts their features and builds an index file for the search engine. Sending each object to the collector is always the worst option with respect to resource usage because it is the feature, not the entire object, which will be used in indexing and retrieval. An alternative is t ....A scheme of local compilation of mobile collectors for image and video search engines. The object collector is an important component in a Web search engine. A collector collects Web objects (text, image, video, etc), extracts their features and builds an index file for the search engine. Sending each object to the collector is always the worst option with respect to resource usage because it is the feature, not the entire object, which will be used in indexing and retrieval. An alternative is to send a collector to the source site, which has an advantage of distributing computational load and performing summarization and compression. This project proposes a locally compiled mobile collector for image and video search engines.Read moreRead less
Effective Information Retrieval for Partitioned Document Collections. Current information retrieval services make use of massive indexes in order to resolve content-based queries. Monolithic approaches like this have been effective until now because the volume of data stored has been manageable on a single machine or tightly-coupled cluster of machines, and because the data has been available for collection. But with an increasing amount of automatically generated data, and an increasing diversi ....Effective Information Retrieval for Partitioned Document Collections. Current information retrieval services make use of massive indexes in order to resolve content-based queries. Monolithic approaches like this have been effective until now because the volume of data stored has been manageable on a single machine or tightly-coupled cluster of machines, and because the data has been available for collection. But with an increasing amount of automatically generated data, and an increasing diversity of information sources, other approaches are required. In this project we will investigate mechanisms for handling retrieval tasks when the indexes to the data are stored locally with the data, and when no central index is viable.Read moreRead less
Methodologies for Designing and Evaluating Information Retrieval Experiments. Australian researchers have been highly successful in the area of information searching for more than two decades. This project will reinforce that position. By developing better measures of how retrieval systems such as web search engines perform, we will be able to advise the providers of such services on how to structure software so as to maximize the utility gained by their customers. Targeted access to the right ....Methodologies for Designing and Evaluating Information Retrieval Experiments. Australian researchers have been highly successful in the area of information searching for more than two decades. This project will reinforce that position. By developing better measures of how retrieval systems such as web search engines perform, we will be able to advise the providers of such services on how to structure software so as to maximize the utility gained by their customers. Targeted access to the right information is a goal of all organizations, regardless of their type, and improved methodologies for conducting information retrieval experiments will have widespread and tangible benefits. The techniques developed will also be applicable in fields such as document categorization, text summarization, and machine learning.Read moreRead less
Static and Dynamic Query Pruning Techniques for Complex Text Retrieval Systems. Targeted access to the right information is a goal of all organizations, regardless of their type, and improved methodologies for implementing information retrieval systems have widespread and tangible benefits. Australian researchers have been highly successful in this area of information searching for more than two decades, and this project will reinforce that position. By developing techniques for providing fast ....Static and Dynamic Query Pruning Techniques for Complex Text Retrieval Systems. Targeted access to the right information is a goal of all organizations, regardless of their type, and improved methodologies for implementing information retrieval systems have widespread and tangible benefits. Australian researchers have been highly successful in this area of information searching for more than two decades, and this project will reinforce that position. By developing techniques for providing faster search, even in the presence of complex query variants and distributed implementations, we will be able to advise the suppliers of such services on how to provide a maximally useful product.
Read moreRead less
AI-driven Effective Query Formulation for Better Systematic Reviews. This project aims to develop novel AI-based search engine methods to make the creation of systematic reviews cheaper, faster and unbiased. Systematic reviews are the cornerstone for evidence-based decisions in clinical practice and government policy making. Given the pace new research is published at, it is unsustainable to manually conduct systematic reviews in the traditional manner, taking on average 2 years and $350K and be ....AI-driven Effective Query Formulation for Better Systematic Reviews. This project aims to develop novel AI-based search engine methods to make the creation of systematic reviews cheaper, faster and unbiased. Systematic reviews are the cornerstone for evidence-based decisions in clinical practice and government policy making. Given the pace new research is published at, it is unsustainable to manually conduct systematic reviews in the traditional manner, taking on average 2 years and $350K and becoming already outdated when published. The outcomes of this project will lead to systematic reviews of higher quality, while reducing their financial and temporal costs, providing significant benefits to organisations performing reviews and their funders, and to people impacted by decisions made from the reviews.Read moreRead less
Finding answers for complex questions. This project aims to develop a new search paradigm for on-line search engines that presents users with answers to complex questions, rather than forcing them to find answers themselves from lists of retrieved documents. The project will develop a taxonomy of complex answer search tasks, devise novel techniques to increase the effectiveness of complex answer retrieval through interaction and, create a new evaluation framework for precise measurement of syste ....Finding answers for complex questions. This project aims to develop a new search paradigm for on-line search engines that presents users with answers to complex questions, rather than forcing them to find answers themselves from lists of retrieved documents. The project will develop a taxonomy of complex answer search tasks, devise novel techniques to increase the effectiveness of complex answer retrieval through interaction and, create a new evaluation framework for precise measurement of system effectiveness. This project should provide significant advances that will benefit all users of search engines.Read moreRead less