4 papers
Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral
Ayoub Hammal, Pierre Zweigenbaum, Caio Corro
Several previous works concluded that the largest part of generation capabilities of large language models (LLM) are learned (early) during pre-training. However, LLMs still requir…
DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures
Benno Uthayasooriyar, Antoine Ly, Franck Vermet +1
We introduce DocPolarBERT, a layout-aware BERT model for document understanding that eliminates the need for absolute 2D positional embeddings. We extend self-attention to take int…
Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain
Benno Uthayasooriyar, Antoine Ly, Franck Vermet +1
Generic pre-trained neural networks may struggle to produce good results in specialized domains like finance and insurance. This is due to a domain mismatch between training data a…
Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection
Ayoub Hammal, Benno Uthayasooriyar, Caio Corro
Named-entity recognition (NER) is a task that typically requires large annotated datasets, which limits its applicability across domains with varying entity definitions. This paper…