This report describes the system developed by the University of Edinburgh and the University of Sydney for the TREC-2005 question answering evaluation exercise. The backbone of our question-answering platform is QED, a linguistically-principled QA system. We experimented with external sources of knowledge, such as Google and Wikipedia, to enhance the performance of QED, especially for reranking and off-line processing of the corpus. For factoid and list questions we performed significantly above the median accuracy score of all participating systems at TREC 2005
This paper describes a new version of the DIOGENE Question Answering (QA) system developed at ITC-Ir...
The TREC 2004 Question Answering track contained a single task in which question series were used to...
This is the second year that Dalhousie University actively participated in TREC. Three runs were su...
This report describes the system developed by the University of Edinburgh and the University of Sy...
In the QA and information retrieval domains progress has been assessed via evaluation campaigns(Clef...
This paper describes the experiments of the TALP-UPC group for factoid and ’other ’ (definitional) q...
We describe our first participation in TREC. We only competed in the Question Answering category and...
We describe our participation in the TREC 2004 Question Answering track. We provide a detailed accou...
This paper describes the experiments of the TALP-UPC group for factoid and ’other’ (definitional) qu...
The TREC 2004 Question Answering track contained a single task in which question series were used to...
The QACTIS system is being developed for the eventual purpose of providing a user the capability of ...
AnswerFinder has been completely redesigned for TREC 2005. The new architecture allows a fast develo...
The TREC 2003 question answering track contained two tasks, the passages task and the main task. In ...
Our QA system consists of two different components. One is for the factoid and list questions, and t...
runs to factoids. Our approach was to use our open domain QA system that finds the answer among Web ...
This paper describes a new version of the DIOGENE Question Answering (QA) system developed at ITC-Ir...
The TREC 2004 Question Answering track contained a single task in which question series were used to...
This is the second year that Dalhousie University actively participated in TREC. Three runs were su...
This report describes the system developed by the University of Edinburgh and the University of Sy...
In the QA and information retrieval domains progress has been assessed via evaluation campaigns(Clef...
This paper describes the experiments of the TALP-UPC group for factoid and ’other ’ (definitional) q...
We describe our first participation in TREC. We only competed in the Question Answering category and...
We describe our participation in the TREC 2004 Question Answering track. We provide a detailed accou...
This paper describes the experiments of the TALP-UPC group for factoid and ’other’ (definitional) qu...
The TREC 2004 Question Answering track contained a single task in which question series were used to...
The QACTIS system is being developed for the eventual purpose of providing a user the capability of ...
AnswerFinder has been completely redesigned for TREC 2005. The new architecture allows a fast develo...
The TREC 2003 question answering track contained two tasks, the passages task and the main task. In ...
Our QA system consists of two different components. One is for the factoid and list questions, and t...
runs to factoids. Our approach was to use our open domain QA system that finds the answer among Web ...
This paper describes a new version of the DIOGENE Question Answering (QA) system developed at ITC-Ir...
The TREC 2004 Question Answering track contained a single task in which question series were used to...
This is the second year that Dalhousie University actively participated in TREC. Three runs were su...