Learning Multi-level Dependencies for Robust Word Recognition
This addresses the problem of brittle language processing systems for applications requiring robustness to noise, though it appears incremental.
The paper tackles robust word recognition in noisy sentences by capturing multi-level sequential dependencies, and the proposed framework outperforms state-of-the-art methods by a large margin.
Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises. In this paper, we introduce a robust word recognition framework that captures multi-level sequential dependencies in noised sentences. The proposed framework employs a sequence-to-sequence model over characters of each word, whose output is given to a word-level bi-directional recurrent neural network. We conduct extensive experiments to verify the effectiveness of the framework. The results show that the proposed framework outperforms state-of-the-art methods by a large margin and they also suggest that character-level dependencies can play an important role in word recognition.