@article {13657, title = {Tagging and Parsing of Bilingual Dictionary}, volume = {LAMP-TR-106,CFAR-TR-991,CS-TR-4529,UMIACS-TR-2003-97}, year = {2003}, month = {2003/09//}, institution = {University of Maryland, College Park}, abstract = {Bilingual dictionaries hold great potential as a source of lexical resources for training and testing automated systems for optical character recognition, machine translation, and cross-language information retrieval. In this paper, we describe a system for extracting term lexicons from printed bilingual dictionaries. Our work was divided into three phases - dictionary segmentation, entry tagging, and generation. In segmentation, pages are divided into logical entries based on structural features learned from selected examples. The extracted entries are associated with functional labels and passed to a tagging module which associates linguistic labels with each word or phrase in the entry. The output of the system is a structure that represents the entries from the dictionary. We have used this approach to parse a variety of dictionaries with both Latin and non-Latin alphabets, and demonstrate the results of term lexicon generation for retrieval from a collection of French news stories using English queries.}, author = {Ma,Huanfeng and Karagol-Ayan,Burcu and David Doermann and Oard, Douglas and Wang,Jianqiang} }