Search Results for author:
Found 4 papers, 3 papers with code
Recurrent Linear Transformers
In this paper we introduce recurrent alternatives to the transformer self-attention mechanism that offer a context-independent inference cost, leverage long-range dependencies effectively, and perform well in practice.
Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning
Recent approaches in literature have exploited the multi-modal information in documents (text, layout, image) to serve specific downstream document tasks.
OmniNet: A unified architecture for multi-modal multi-task learning
We also show that using this neural network pre-trained on some modalities assists in learning unseen tasks such as video captioning and video question answering.
Text normalization using memory augmented neural networks
We perform text normalization, i. e. the transformation of words from the written to the spoken form, using a memory augmented neural network.
