Search Results for author:
Found 6 papers, 1 papers with code
Structured Pruning Adapters
To improve on this, we propose Structured Pruning Adapters (SPAs), a family of compressing, task-switching network adapters, that accelerate and specialize networks using tiny parameter sets and structured pruning.
Design Considerations For Hypothesis Rejection Modules In Spoken Language Understanding Systems
Hypothesis rejection modules in both schemes reject/accept a hypothesis based on features drawn from the utterance directed to the SLU system, the associated SLU hypothesis and SLU confidence score.
ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification
We make use of a conditional generator for data augmentation that is trained directly using the meta-learning objective and simultaneously with prototypical networks, hence ensuring that data augmentation is customized to the task.
Automatic Discovery of Novel Intents & Domains from Text Utterances
We propose a novel framework, ADVIN, to automatically discover novel domains and intents from large volumes of unlabeled data.
Towards classification parity across cohorts
In this research work, we aim to achieve classification parity across explicit as well as implicit sensitive features.
One-vs-All Models for Asynchronous Training: An Empirical Analysis
An OVA system consists of as many OVA models as the number of classes, providing the advantage of asynchrony, where each OVA model can be re-trained independent of other models.
