A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts

TL;DR

This paper introduces a few-shot learning method for N-gram spotting in historical manuscripts, reducing vocabulary dependency and improving recognition with limited labeled data.

Contribution

It proposes a novel multi-representation few-shot approach for N-gram spotting, addressing data scarcity in historical manuscript recognition.

Findings

Achieved promising results on Bentham's manuscripts

Reduced out-of-vocabulary word issues

Demonstrated effectiveness of few-shot N-gram spotting

Abstract

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.