A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts
This addresses the challenge of out-of-vocabulary words in historical document analysis for researchers and archivists, though it is incremental as it builds on existing keyword spotting methods.
The paper tackles the problem of recognizing text in historical manuscripts with limited labeled data by proposing a few-shot learning approach for spotting n-grams, reducing dependency on a fixed vocabulary and achieving promising results on Bentham's manuscript collections.
Despite recent advances in automatic text recognition, the performance remains moderate when it comes to historical manuscripts. This is mainly because of the scarcity of available labelled data to train the data-hungry Handwritten Text Recognition (HTR) models. The Keyword Spotting System (KWS) provides a valid alternative to HTR due to the reduction in error rate, but it is usually limited to a closed reference vocabulary. In this paper, we propose a few-shot learning paradigm for spotting sequences of a few characters (N-gram) that requires a small amount of labelled training data. We exhibit that recognition of important n-grams could reduce the system's dependency on vocabulary. In this case, an out-of-vocabulary (OOV) word in an input handwritten line image could be a sequence of n-grams that belong to the lexicon. An extensive experimental evaluation of our proposed multi-representation approach was carried out on a subset of Bentham's historical manuscript collections to obtain some really promising results in this direction.