Title
N-gram vs. keyword-based passage retrieval for question answering
Abstract
In this paper we describe the participation of the Universidad Politécnica of Valencia to the 2006 edition, which was focused on the comparison between a Passage Retrieval engine (JIRS) specifically aimed to the Question Answering task and a standard, general use search engine such as Lucene. JIRS is based on n-grams, Lucene on keywords. We participated in three monolingual tasks: Spanish, Italian and French. The obtained results show that JIRS is able to return high quality passages, especially in Spanish.
Year
Venue
Keywords
2006
CLEF
universidad polit,passage retrieval engine,general use search engine,high quality passage,question answering,keyword-based passage retrieval,monolingual task,question answering task,search engine
Field
DocType
Volume
Search engine,Question answering,Information retrieval,Computer science,Artificial intelligence,Natural language processing,n-gram
Conference
4730
ISSN
ISBN
Citations 
0302-9743
3-540-74998-5
10
PageRank 
References 
Authors
0.98
9
4
Name
Order
Citations
PageRank
Davide Buscaldi143654.12
José M. Gómez2328.02
paolo rosso31831188.74
Emilio Sanchis423135.82