Search Results for author:
Found 3 papers, 0 papers with code
Learning to Control Latent Representations for Few-Shot Learning of Named Entities
Our proposed solution is straightforward and simple: we train a controller to execute an optimal sequence of reading and writing operations on an external memory with the goal of leveraging diverse activations from the past and provide accurate predictions.
Aging Memories Generate More Fluent Dialogue Responses with Memory Augmented Neural Networks
By storing KB embeddings into a memory component, these models can learn meaningful representations that are grounded to external knowledge.
Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise
While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT) and Text-to-Speech (TTS) systems, the question remains how to best leverage state-of-the-art language models (which capture rich semantic features, but are trained on only written text) on inputs with ASR errors.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
