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
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
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
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
Indexes Allowing Fast and Efficient Text Search. Since the arrival of search engines such as Google, it has become an expectation that we can find a few words in a very large amount of text very quickly. This is also true of biologists, who expect to be able to submit protein sequences for matching against a massive database and retrieve and answer in seconds. If successful, this project will invent fundamental software that will allow the discovery of words in text much more quickly, and using ....Indexes Allowing Fast and Efficient Text Search. Since the arrival of search engines such as Google, it has become an expectation that we can find a few words in a very large amount of text very quickly. This is also true of biologists, who expect to be able to submit protein sequences for matching against a massive database and retrieve and answer in seconds. If successful, this project will invent fundamental software that will allow the discovery of words in text much more quickly, and using less computing resources than current methods. The benefits of this technology to the searching public, scientists, and industry will be immediate as productivity will be improved and costs reduced.Read moreRead less
Sub-collection retrieval: understanding and improving search engines. Search engines have become essential in many parts of daily life. This project aims to improve the accuracy of search engines, increasing the productivity of information seeking tasks and reducing frustration with poor search answers, thus improving the current gateway to the world of information.
Effective summaries for search results. All information retrieval systems return a search result page that lists short summaries of each retrieved document. This project will transform search effectiveness by taking a new approach to the understanding, design, and construction of such summaries. Recent work has showed that users fail to click on up to 50 per cent of relevant documents because of poor summary quality. To enhance search result summaries, this project will model how users determine ....Effective summaries for search results. All information retrieval systems return a search result page that lists short summaries of each retrieved document. This project will transform search effectiveness by taking a new approach to the understanding, design, and construction of such summaries. Recent work has showed that users fail to click on up to 50 per cent of relevant documents because of poor summary quality. To enhance search result summaries, this project will model how users determine document relevance when inspecting a summary; it will exploit a previously untapped source of information to dramatically improve summary quality; and, it will create a new approach to retrieving relevant documents by considering their summarisability.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE0668542
Funder
Australian Research Council
Funding Amount
$425,000.00
Summary
Multimedia Computing, Production, Management and Distribution for HDTV and its Applications. Australia is the first country to launch digital TV nationally. Increasingly, this platform will be used for consuming multimedia information; also the HDTV infrastructure is being applied to other domains such as telemedicine/e-Health to lower costs and improve effectiveness. For Australia to be a step ahead in the development of these applications that are beneficial to a wider community, we have to lo ....Multimedia Computing, Production, Management and Distribution for HDTV and its Applications. Australia is the first country to launch digital TV nationally. Increasingly, this platform will be used for consuming multimedia information; also the HDTV infrastructure is being applied to other domains such as telemedicine/e-Health to lower costs and improve effectiveness. For Australia to be a step ahead in the development of these applications that are beneficial to a wider community, we have to look forward and establish adequate infrastructure for the development of needed applications of the future. It is strongly believed that by doing so we can position ourselves ahead of other communities in anticipating and providing essential services to our modern society and this in turn will greatly benefit the Australian economy.Read moreRead less