@inproceedings{9b7f502509eb40ceac2938ea3f902452,
title = "Automatic expansion of abbreviations in Chinese news text",
abstract = "This paper presents an n-gram based approach to Chinese abbreviation expansion. In this study, we distinguish reduced abbreviations from non-reduced abbreviations that are created by elimination or generalization. For a reduced abbreviation, a mapping table is compiled to map each short-word in it to a set of long-words, and a bigram based Viterbi algorithm is thus applied to decode an appropriate combination of long-words as its full-form. For a non-reduced abbreviation, a dictionary of non-reduced abbreviation/full-form pairs is used to generate its expansion candidates, and a disambiguation technique is further employed to select a proper expansion based on bigram word segmentation. The evaluation on an abbreviation-expanded corpus built from the PKU corpus showed that the proposed system achieved a recall of 82.9% and a precision of 85.5% on average for different types of abbreviations in Chinese news text.",
author = "Guohong Fu and Luke, {Kang Kwong} and Zhou, {Guo Dong} and Ruifeng Xu",
year = "2006",
doi = "10.1007/11880592_42",
language = "English",
isbn = "3540457801",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "530--536",
booktitle = "Information Retrieval Technology - Third Asia Information Retrieval Symposium, AIRS 2006, Proceedings",
address = "Germany",
note = "3rd Asia Information Retrieval Symposium, AIRS 2006 ; Conference date: 16-10-2006 Through 18-10-2006",
}