N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition
This work addresses the problem of adapting handwritten text recognition models to new language distributions, which is significant for applications where the target corpus has a different language distribution than the training data.
The authors tackled the problem of language distribution shift in handwritten text recognition, achieving a significant reduction in the performance gap between source and target corpora. Their approach resulted in improved recognition accuracy despite the language shift.
Transformer-based encoder-decoder networks have recently achieved impressive results in handwritten text recognition, partly thanks to their auto-regressive decoder which implicitly learns a language model. However, such networks suffer from a large performance drop when evaluated on a target corpus whose language distribution is shifted from the source text seen during training. To retain recognition accuracy despite this language shift, we propose an external n-gram injection (NGI) for dynamic adaptation of the network's language modeling at inference time. Our method allows switching to an n-gram language model estimated on a corpus close to the target distribution, therefore mitigating bias without any extra training on target image-text pairs. We opt for an early injection of the n-gram into the transformer decoder so that the network learns to fully leverage text-only data at the low additional cost of n-gram inference. Experiments on three handwritten datasets demonstrate that the proposed NGI significantly reduces the performance gap between source and target corpora.