Word Shape Matters: Robust Machine Translation with Visual Embedding
arXiv:2010.09997
Abstract
Neural machine translation has achieved remarkable empirical performance over standard benchmark datasets, yet recent evidence suggests that the models can still fail easily dealing with substandard inputs such as misspelled words, To overcome this issue, we introduce a new encoding heuristic of the input symbols for character-level NLP models: it encodes the shape of each character through the images depicting the letters when printed. We name this new strategy visual embedding and it is expected to improve the robustness of NLP models because humans also process the corpus visually through printed letters, instead of machinery one-hot vectors. Empirically, our method improves models' robustness against substandard inputs, even in the test scenario where the models are tested with the noises that are beyond what is available during the training phase.
References in corpus (14)
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Training Very Deep Networks
- Character-Aware Neural Language Models
- Achieving Human Parity on Automatic Chinese to English News Translation
- Deep Text Classification Can be Fooled
- Synthetic and Natural Noise Both Break Neural Machine Translation
- Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
- HotFlip: White-Box Adversarial Examples for Text Classification
- tax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification
- High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
- Robust Neural Machine Translation with Doubly Adversarial Inputs
- Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis
- Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation
- Super Characters: A Conversion from Sentiment Classification to Image Classification