Fast Search with Poor OCR
This addresses the challenge of indexing and searching digitized historical collections for researchers and archivists, but it is an incremental improvement as it adapts existing vector-based techniques to noisy text.
The paper tackles the problem of searching historical documents with poor OCR quality by proposing a text-based method that projects queries and candidates into a common vector space for ranking, demonstrating its practicality on WWII-era German typewritten documents.
The indexing and searching of historical documents have garnered attention in recent years due to massive digitization efforts of important collections worldwide. Pure textual search in these corpora is a problem since optical character recognition (OCR) is infamous for performing poorly on such historical material, which often suffer from poor preservation. We propose a novel text-based method for searching through noisy text. Our system represents words as vectors, projects queries and candidates obtained from the OCR into a common space, and ranks the candidates using a metric suited to nearest-neighbor search. We demonstrate the practicality of our method on typewritten German documents from the WWII era.