10 citations · 39 across the 10 of their papers we have counts for
5 papers · 1 filter
A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset
Vahid Noroozi, Yang Zhang, Evelina Bakhturina +1
Dialog State Tracking (DST) is one of the most crucial modules for goal-oriented dialogue systems. In this paper, we introduce FastSGT (Fast Schema Guided Tracker), a fast and robu…
PyTorchPipe: a framework for rapid prototyping of pipelines combining language and vision
Tomasz Kornuta
Access to vast amounts of data along with affordable computational power stimulated the reincarnation of neural networks. The progress could not be achieved without adequate softwa…
Learning to Remember, Forget and Ignore using Attention Control in Memory
T. S. Jayram, Younes Bouhadjar, Ryan L. McAvoy +4
Typical neural networks with external memory do not effectively separate capacity for episodic and working memory as is required for reasoning in humans. Applying knowledge gained…
Using Multi-task and Transfer Learning to Solve Working Memory Tasks
T. S. Jayram, Tomasz Kornuta, Ryan L. McAvoy +1
We propose a new architecture called Memory-Augmented Encoder-Solver (MAES) that enables transfer learning to solve complex working memory tasks adapted from cognitive psychology.…
Surprisal-Driven Zoneout
Kamil Rocki, Tomasz Kornuta, Tegan Maharaj
We propose a novel method of regularization for recurrent neural networks called suprisal-driven zoneout. In this method, states zoneout (maintain their previous value rather than…