Lifelong learning for text retrieval and recognition in historical handwritten document collections

TL;DR

This paper discusses the development of a lifelong learning system for text retrieval and recognition in large, diverse collections of historical handwritten documents, emphasizing scalability and evolving ground truth.

Contribution

It introduces the 'ball-park principle' to guide the transition from traditional to deep learning methods based on data labeling levels.

Findings

Deep learning offers high potential but requires scalable data labeling.

The 'ball-park principle' helps manage the evolution of learning approaches.

The system addresses variability across scripts and languages in historical documents.

Abstract

This chapter provides an overview of the problems that need to be dealt with when constructing a lifelong-learning retrieval, recognition and indexing engine for large historical document collections in multiple scripts and languages, the Monk system. This application is highly variable over time, since the continuous labeling by end users changes the concept of what a 'ground truth' constitutes. Although current advances in deep learning provide a huge potential in this application domain, the scale of the problem, i.e., more than 520 hugely diverse books, documents and manuscripts precludes the current meticulous and painstaking human effort which is required in designing and developing successful deep-learning systems. The ball-park principle is introduced, which describes the evolution from the sparsely-labeled stage that can only be addressed by traditional methods or nearest-neighbor methods on embedded vectors of pre-trained neural networks, up to the other end of the spectrum where massive labeling allows reliable training of deep-learning methods. Contents: Introduction, Expectation management, Deep learning, The ball-park principle, Technical realization, Work flow, Quality and quantity of material, Industrialization and scalability, Human effort, Algorithms, Object of recognition, Processing pipeline, Performance,Compositionality, Conclusion.