Name
Abstract | ||
|---|---|---|
Current Information Retrieval systems are often based on topicality. They estimate relevance by comparing the similarity between the user query and each document. These systems do not take into account important contextual information. More specifically, they do not often apply mechanisms to filter out redundant information. We interpret context here as the set of chunks of text from the ranked set of documents that the user has already seen. This is a valuable contextual information to guide the retrieval processes in a way that avoids redundancy. It is desirable that the ranking of results is composed by relevant but also novel material. This means that each document must provide to the user unseen information which is related to his need. In this work we study different novelty detection approaches that make good use of this contextual information. We show that these techniques can be applied effectively and efficiently at the sentence level. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1145/1414694.1414703 | IIiX |
Keywords | Field | DocType |
user unseen information,account important contextual information,avoids redundancy,redundant information,valuable contextual information,different novelty detection approach,good use,current information retrieval system,user query,mixture model,contextual information,efficient kld model,contextual re-ranking,information retrieval system,query expansion | Data mining,Query language,Cognitive models of information retrieval,Novelty detection,Human–computer information retrieval,Information retrieval,Ranking,Query expansion,Computer science,Ranking (information retrieval),Relevance (information retrieval) | Conference |
Citations | PageRank | References |
0 | 0.34 | 14 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ronald T. Fernández | 1 | 33 | 3.78 |
| David E. Losada | 2 | 326 | 40.63 |