@inproceedings{42a3f661c6bf4f86ad8eb932f614466d,
title = "An Investigation of Decompounding for Cross-language Patent Search",
abstract = "Decompounding has been found to improve information retrieval (IR) effectiveness in general domains for languages such as German or Dutch. We investigate if cross-language patent retrieval can profit from decompounding. This poses two challenges: i) There may be few resources such as parallel corpora available for training an machine translation system for a compounding language. ii) Patents have a specific writing style and vocabulary ({"}patentese{"}), which may affect the performance of decompounding and translation methods. Experiments on data from the CLEF-IP 2010 task show that decompounding patents for translation can overcome out-of-vocabulary problems (OOV) and that decompounding improves IR performance significantly for small training corpora.",
author = "Johannes Leveling and Walid Magdy and Jones, \{Gareth J.F.\}",
year = "2011",
doi = "10.1145/2009916.2010103",
language = "English",
isbn = "978-1-4503-0757-4",
series = "SIGIR '11",
publisher = "ACM",
pages = "1169--1170",
booktitle = "Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval",
}