Learning Multi-level Dependencies for Robust Word Recognition
arXiv:1911.09789
Abstract
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.
References in corpus (8)
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Generating Natural Adversarial Examples
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
- Synthetic and Natural Noise Both Break Neural Machine Translation
- HotFlip: White-Box Adversarial Examples for Text Classification
- Combating Adversarial Misspellings with Robust Word Recognition
- A Nested Attention Neural Hybrid Model for Grammatical Error Correction
- Say What I Want: Towards the Dark Side of Neural Dialogue Models