Active Learning with Tabular Language Models
This work addresses the challenge of expensive expert annotation for technical tables in industry, though it is incremental as it applies known active learning methods to a new context.
The paper tackled the problem of high labeling costs for domain-specific tables in industrial settings by applying active learning to tabular language models for sub-cell named entity recognition, showing that cell-level acquisition functions with built-in diversity significantly reduce labeling effort.
Despite recent advancements in tabular language model research, real-world applications are still challenging. In industry, there is an abundance of tables found in spreadsheets, but acquisition of substantial amounts of labels is expensive, since only experts can annotate the often highly technical and domain-specific tables. Active learning could potentially reduce labeling costs, however, so far there are no works related to active learning in conjunction with tabular language models. In this paper we investigate different acquisition functions in a real-world industrial tabular language model use case for sub-cell named entity recognition. Our results show that cell-level acquisition functions with built-in diversity can significantly reduce the labeling effort, while enforced table diversity is detrimental. We further see open fundamental questions concerning computational efficiency and the perspective of human annotators.