Regular expressions for decoding of neural network outputs
This provides a convenient tool for applications like information retrieval and full text recognition, though it is an incremental improvement in decoding methods for neural networks.
The authors tackled the problem of decoding neural network outputs in handwritten text recognition by proposing a decoder based on regular expressions and finite automata, achieving a great speed-up through approximation while maintaining efficiency compared to other methods.
This article proposes a convenient tool for decoding the output of neural networks trained by Connectionist Temporal Classification (CTC) for handwritten text recognition. We use regular expressions to describe the complex structures expected in the writing. The corresponding finite automata are employed to build a decoder. We analyze theoretically which calculations are relevant and which can be avoided. A great speed-up results from an approximation. We conclude that the approximation most likely fails if the regular expression does not match the ground truth which is not harmful for many applications since the low probability will be even underestimated. The proposed decoder is very efficient compared to other decoding methods. The variety of applications reaches from information retrieval to full text recognition. We refer to applications where we integrated the proposed decoder successfully.