Dzmitry Bahdanau

Towards Ecologically Valid Research on Language User Interfaces

2020 · arXiv (Cornell University)

Language User Interfaces (LUIs) could improve human-machine interaction for a wide variety of tasks, such as playing music, getting insights from databases, or instructing domestic robots. In contrast to traditional hand-crafted approaches, recent work attempts …

Data Augmentation for Intent Classification with Off-the-shelf Large Language Models

2022 · arXiv (Cornell University)

Data augmentation is a widely employed technique to alleviate the problem of data scarcity. In this work, we propose a prompting-based approach to generate labelled training data for intent classification with off-the-shelf language models (LMs) …

End-to-end attention-based large vocabulary speech recognition

2016

Many state-of-the-art Large Vocabulary Continuous Speech Recognition (LVCSR) Systems are hybrids of neural networks and Hidden Markov Models (HMMs). Recently, more direct end-to-end methods have been investigated, in which neural architectures were trained to model …

An Actor-Critic Algorithm for Sequence Prediction

2016 · arXiv (Cornell University)

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Current log-likelihood training methods are limited by the discrepancy between their training and testing modes, as models …

Attention-Based Models for Speech Recognition

2015 · arXiv (Cornell University)

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We extend …