Passage Retrieval is a crucial step in question answering systems, one that has been well researched in the past. Due to the vocabulary mismatch problem and independence assumption of bag-of-words retrieval models, correct passages are often ranked lower than other incorrect passages in the retrieved list. Whereas in previous work, passages are reranked only on the basis of syntactic structures...

This paper describes the four systems RMIT fielded for the TREC 2015 LiveQA task and the associated experiments. The challenge results show that the base run RMIT-0 has achieved an above-average performance, but other attempted improvements have all resulted in decreased retrieval effectiveness. Keywords-TREC LiveQA 2015; RMIT; passage retrieval; summarization; query trimming; headword expansion

In this paper we describe the planned setup of the INEX 2006 interactive track. As the track has been delayed and data collection has not been completed before the INEX 2006 workshop, the track will continue into 2007. Special emphasis is put on comparing XML element retrieval with passage retrieval, and on investigating differences between multiple dimensions of the search tasks.

In the context of information retrieval, we propose here to merge in a single mathematical framework: the Boolean model, the vector space model, and passage retrieval in a single mathematical framework based on signal theory. In this framework, we define the weight wd,t of the term t in the document d not as a number, but as a function.

This paper describes the method we used for the Genomics Track of TREC 2006. BM25 model is implemented to retrieve relevant documents. We also tried to re-ranking documents based on the initial retrieval before passage retrieval. Passages are retrieved based on the concepts defining in topics and concept coverage. Results of submitted runs are listed and discussed.

This paper describes the results of some experiments using a new approach to information access that combines techniques from natural language processing and knowledge representation with a penalty based technique for relevance estimation and passage retrieval. Unlike many attempts to combine natural language processing with information retrieval, these results show substantial benefit from usi...

This paper presents the results of our participation in the relevance feedback track using our novel retrieval models. These models simulate human relevance decision-making. For each document location of a query term, information from its document-context at that location determines the relevance decision outcomes there. The relevance values for all documents locations of all query terms in the...

The primary goal of the SMART information retrieval project at CorneU University remains, as it has for the past 30 years, investigating the effectiveness and efficiency of automatic methods of retrieval of text. In recent years this has expanded to include retrieval of parts of documents in response to both user queries (passage retrieval) and parts of other documents (automatic hypertext link...

In NTCIR-5, we used five retrieval methods proposed in NTCIR-4: (1) query term weighting using only document frequency, (2) stopword deletion, (3) two-stage patent retrieval, (4) term weighting considering “measurement terms”, and (5) related term expansion. In this paper, we compare the retrieval accuracy for two test sets: 34 main queries in NTCIR-4 and 1189 new queries in NTCIR-5. Then, we e...