@inproceedings{099b924d7e91483088f872ff92986d6e,
title = "Collaborative Recognition and Recovery of the Chinese Intercept Abbreviation",
abstract = "One of the important works of Information Content Security is evaluating the theme words of the text. Because of the variety of the Chinese expression, especially of the abbreviation, the supervision of the theme words becomes harder. The goal of this paper is to quickly and accurately discover the intercept abbreviations from the text crawled at the short time period. The paper firstly segments the target texts, and then utilizes the Supported Vector Machine (SVM) to recognize the abbreviations from the wrongly segmented texts as the candidates. Secondly, this paper presents the collaborative methods: Improve the Conditional Random Fields (CRF) to predict the corresponding word to each character of the abbreviation; To solve the problems of the 1:n relationship, collaboratively merge the ranking list from the predict steps with the matched results of the thesaurus of abbreviations. The experiments demonstrate that our method at the recognizing stage is 76.5% of the accuracy and 77.8% of the recall rate. At the recovery step, the accuracy is 62.1%, which is 20.8% higher than the method based on Hidden Markov Model (HMM).",
keywords = "Chinese abbreviation, Collaborative recovery, Improved CRF",
author = "Jinshuo Liu and Yusen Chen and Juan Deng and Donghong Ji and Jeff Pan",
year = "2017",
month = oct,
day = "7",
doi = "10.1007/978-3-319-69005-6_19",
language = "English",
isbn = "9783319690049",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer-Verlag",
pages = "224--236",
editor = "Maosong Sun and Baobao Chang and Xiaojie Wang and Deyi Xiong",
booktitle = "Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data - 16th China National Conference, CCL 2017 and 5th International Symposium, NLP-NABD 2017, Proceedings",
note = "16th China National Conference on Computational Linguistics, CCL 2017 and 5th International Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2017 ; Conference date: 13-10-2017 Through 15-10-2017",
}