W03-2003 Abstract We describe the overview of patent retrieval task at NTCIR-3 . The main task
D13-1175 ) who use pairwise ranking for patent retrieval . Their method is a classical
E12-1012 the MAP scores for Cross-Lingual Patent Retrieval . However , the topics in patent
W03-2000 first ACM SIGIR 2000 Workshop on Patent Retrieval was held . In this work - shop
S10-1055 has been created for improving patent retrieval and classification ( Lopez and
P00-1062 information retrieval ( e.g. , a patent retrieval ) , where every relevant document
W03-2003 Participants could try cross-lingual patent retrieval by using one of the non-Japanese
D13-1175 query . Furthermore , we use the Patent Retrieval Evaluation Score ( PRES ) 15
W03-2000 to evaluate mono/cross-lingual patent retrieval systems . In addition , approximately
D13-1175 Cross-language Learning-to - Rank for Patent Retrieval " . We would like to thank Eugen
D13-1023 based on corpora of the NTCIR patent retrieval task ( Atsushi Fujii et al. ,
D13-1175 extract relevance judgements for patent retrieval from patent citations . The key
D13-1175 useful to automatically create a patent retrieval dataset for our experiments .
D13-1175 in-domain datasets . Furthermore , our patent retrieval setup gives SMT-based approaches
W03-2003 blocking factor . <title> Overview of Patent Retrieval Task at NTCIR-3 </title> Makoto
D15-1069 full text note . 2 Related Work Patent retrieval ( Fujii et al. , 2007 ) is similar
D13-1175 technique is useful to develop patent retrieval systems , it would be interesting
P12-1002 Cross-language Learning-to - Rank for Patent Retrieval " . Chris Dyer was supported
D15-1069 et al. , 2012 ) . However , the patent retrieval domain is recall-driven , while
D15-1069 expanded to generate queries in the patent retrieval domain ( Mahd - abi et al. ,
hide detail