RMIT University at the TREC 2007 Enterprise Track
نویسندگان
چکیده
The 2007 document search task is akin to a topic distillation task, where the search system should identify resource pages that provide links to informational pages that are relevant to a broad topic, aiming to provide a rich information space and comprehensive picture between found documents and the topic. Such a page may or may not exist in the website: if it exists, it would be ideal for a search engine to rank the page highly; otherwise, the search engine should retrieve those pages potentially pointed at by such a resource page, and rank these pages highly. Anchor text, PageRank, and Indegree have been shown to be useful sources of external evidence for navigational search tasks. We view the topic distillation task (or this year’s document search task) as lying somewhere between navigational and informational searches on the spectrum of search tasks. Therefore, as a starting point, we investigate if external sources of evidence such as anchor text are also useful for such a task. We used the Lemur toolkit [1] for indexing and searching for all of our submitted runs. Answer documents are ranked according to their KL divergence.
منابع مشابه
RMIT University at TREC 2004
RMIT University participated in two tracks at TREC 2004: Terabyte and Genomics, both for the first time. This paper describes the techniques we applied and our experiments in both tracks, and discusses the results of the genomics track runs; the terabyte track results are unavailable at the time of manuscript submission. We also describe our new zettair search engine, in use for the first time ...
متن کاملRMIT University at TREC 2008: Relevance Feedback Track
This report outlines TREC-2008 Relevance Feedback Track experiments done at RMIT University. Relevance feedback in text retrieval systems is a process where a user gives explicit feedback on an initial set of retrieval results returned by a search system. For example, the user might mark some of the items as being relevant, or not relevant, to their current information need. This feedback can b...
متن کاملUniversity of Twente at the TREC 2008 Enterprise Track: Using the Global Web as an Expertise Evidence Source
This paper describes the details of our participation in expert search task of the TREC 2007 Enterprise track.
متن کاملRMIT University at TREC 2008: Legal Track
This paper reports on the participation of RMIT university in the 2008 TREC Legal Track Ad Hoc task. OCR errors can corrupt the document view formed by an information retrieval system, and substantially hinder the successful retrieval of relevant documents for user queries. In previous research, the presence of errors in OCR text was observed to lead to unstable and unpredictable retrieval effe...
متن کاملRMIT University at TREC 2009: Web Track
RMIT participated in the 2009 Web Track tasks. Our submissions utilised the Zettair search engine1 to index and search the Category B subset of the ClueWeb collection used by the Web Track. The Web Track was composed of two tasks, a traditional adhoc retrieval task, and a new diversity task where participants attempted to retrieve documents covering a range of sub topics for each query. Sub top...
متن کامل