Title
“How much context do you need?”: an experiment about the context size in interactive cross-language question answering
Abstract
The main topic of this paper is the context size needed for an efficient Interactive Cross-language Question Answering system. We compare two approaches: the first one (baseline system) shows the user whole passages (maximum context: 10 sentences). The second one (experimental system) shows only a clause (minimum context). As cross-language system, the main problem is that the language of the question (Spanish) and the language of the answer context (English) are different. The results show that large context is better. However, there are specific relations between the context size and the knowledge about the language of the answer: users with poor level of English prefer context with few words.
Year
DOI
Venue
2005
10.1007/11878773_32
CLEF (Working Notes)
Keywords
Field
DocType
interactive cross-language question answering,experimental system,minimum context,maximum context,baseline system,cross-language system,large context,main problem,context size,answering system,answer context,question answering,question answering system
Information system,Question answering,Computer science,Multilingualism,Phrase,Natural language,Natural language processing,Artificial intelligence,Baseline system,Cross language question answering,Sentence
Conference
Volume
ISSN
ISBN
4022
0302-9743
3-540-45697-X
Citations 
PageRank 
References 
3
0.48
14
Authors
6
Name
Order
Citations
PageRank
Borja Navarro117317.65
Lorenza Moreno-Monteagudo282.69
Elisa Noguera34710.35
Sonia Vázquez4173.40
Fernando Llopis5204.33
Andrés Montoyo667867.78