On Building a Full-Text Digital Library of Historical Documents Szu-Pei Chen 1 , Jieh Hsiang 1† , Hsieh-Chang Tu 1 , Micha Wu 2 1 Department of Computer Science and Information Engineering 2 Department of History National Taiwan University, Taipei, Taiwan {gail,tu}@turing.csie.ntu.edu.tw, hsiang@csie.ntu.edu.tw, wumc@ntu.edu.tw Abstract. The National Taiwan University Library has built a digital library of historical documents about Taiwan. The content is unique in that it covers about 80% of all primary Chinese historical materials about Taiwan before 1895, and that they are all available in searchable full text, in addition to metadata. To make these materials more accessible to the research community, we have developed, in addition to full-text search and retrieval, a concept of regarding the set of documents retrieved by a query as a sub-collection, and have designed post-query classification methods to help users find the inter-relationships among documents and the collective meaning of a sub-collection. We have also developed techniques for term extraction for old Chinese and a data format for representing governmental structures. We hope that our system will help advance research in Taiwanese history, and will set a model for other similar endeavor. Keywords: historical documents, digital library, Taiwan, classification of query results. 1 Introduction Starting from 2003, the National Taiwan University Library (NTUL) embarked on a major effort to systematically collect and digitize Taiwan related historical documents. The documents, numbered over 80,000, came from a wide range of sources, including imperial court archives, local and central judicial and administrative records, personal records of high-ranking officials, travel journals, diaries of influential people of the time, and land deeds. They were selected by historians, then typed, punctuated, proof- read, and supplemented with metadata records. Currently we have accumulated about 150 million Chinese words (characters), all in full text and searchable. They cover about 80% of all primary Chinese historical materials about Taiwan before 1895. To our knowledge, there has never been such a collection, in both variety and magnitude, about Taiwan history available in searchable full text before. It should † Corresponding author.