no code implementations • Findings (EMNLP) 2021 • Chul Sung, Vaibhava Goel, Etienne Marcheret, Steven Rennie, David Nahamoo
More importantly our fine-tuned CoNLL2003 model displays significant gains in generalization to out of domain datasets: on the OntoNotes subset we achieve an F1 of 72. 67 which is 0. 49 points absolute better than the baseline, and on the WNUT16 set an F1 of 68. 22 which is a gain of 0. 48 points.
no code implementations • EMNLP 2020 • Steven Rennie, Etienne Marcheret, Neil Mallinar, David Nahamoo, Vaibhava Goel
Nevertheless, additional pre-training closer to the end-task, such as training on synthetic QA pairs, has been shown to improve performance.
no code implementations • 17 Oct 2017 • Xiaodong Cui, Vaibhava Goel, George Saon
An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling.
no code implementations • ICML 2017 • Youssef Mroueh, Tom Sercu, Vaibhava Goel
We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN).
31 code implementations • CVPR 2017 • Steven J. Rennie, Etienne Marcheret, Youssef Mroueh, Jarret Ross, Vaibhava Goel
In this paper we consider the problem of optimizing image captioning systems using reinforcement learning, and show that by carefully optimizing our systems using the test metrics of the MSCOCO task, significant gains in performance can be realized.
no code implementations • 28 Nov 2016 • Tom Sercu, Vaibhava Goel
We show that dense prediction view of framewise classification offers several advantages and insights, including computational efficiency and the ability to apply batch normalization.
no code implementations • 25 Oct 2016 • Youssef Mroueh, Etienne Marcheret, Vaibhava Goel
We introduce co-occurring directions sketching, a deterministic algorithm for approximate matrix product (AMM), in the streaming model.
no code implementations • 6 Apr 2016 • Tom Sercu, Vaibhava Goel
We demonstrate the performance of our models both on larger scale data than before, and after sequence training.
no code implementations • 19 Nov 2015 • Youssef Mroueh, Etienne Marcheret, Vaibhava Goel
Joint modeling of language and vision has been drawing increasing interest.
no code implementations • 11 Jun 2015 • Youssef Mroueh, Steven Rennie, Vaibhava Goel
In this paper, we propose and study random maxout features, which are constructed by first projecting the input data onto sets of randomly generated vectors with Gaussian elements, and then outputing the maximum projection value for each set.
no code implementations • 22 Jan 2015 • Youssef Mroueh, Etienne Marcheret, Vaibhava Goel
In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (AV-ASR).
Audio-Visual Speech Recognition Automatic Speech Recognition +3