no code implementations • IWSLT (ACL) 2022 • Oleksii Hrinchuk, Vahid Noroozi, Ashwinkumar Ganesan, Sarah Campbell, Sandeep Subramanian, Somshubra Majumdar, Oleksii Kuchaiev
Our cascade system consists of 1) Conformer RNN-T automatic speech recognition model, 2) punctuation-capitalization model based on pre-trained T5 encoder, 3) ensemble of Transformer neural machine translation models fine-tuned on TED talks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
no code implementations • IWSLT (ACL) 2022 • Daniel Zhang, Jiang Yu, Pragati Verma, Ashwinkumar Ganesan, Sarah Campbell
This paper describes Amazon Alexa AI’s implementation for the IWSLT 2022 shared task on formality control.
1 code implementation • NeurIPS 2021 • Ashwinkumar Ganesan, Hang Gao, Sunil Gandhi, Edward Raff, Tim Oates, James Holt, Mark McLean
HRRs today are not effective in a differentiable solution due to numerical instability, a problem we solve by introducing a projection step that forces the vectors to exist in a well behaved point in space.
no code implementations • Findings (ACL) 2021 • Ashwinkumar Ganesan, Francis Ferraro, Tim Oates
We propose a Bi-Directional Manifold Alignment (BDMA) that learns a non-linear mapping between two manifolds by explicitly training it to be bijective.
no code implementations • EACL (AdaptNLP) 2021 • Ashwinkumar Ganesan, Francis Ferraro, Tim Oates
We present a locality preserving loss (LPL) that improves the alignment between vector space embeddings while separating uncorrelated representations.
no code implementations • 12 Sep 2019 • Chi Zhang, Bryan Wilkinson, Ashwinkumar Ganesan, Tim Oates
Another way to remove that limitation, an optional classification layer, trained on manually annotated DoS attack tweets, to filter out non-attack tweets can be used to increase precision at the expense of recall.
no code implementations • 28 Mar 2019 • Ashwinkumar Ganesan, Pooja Parameshwarappa, Akshay Peshave, ZhiYuan Chen, Tim Oates
In this paper, we proposeaprobabilistic abductive reasoningapproach that augments an exist-ing rule-based IDS (snort [29]) to detect these evolved attacks by (a)Predicting rule conditions that are likely to occur (based on existingrules) and (b) able to generate new snort rules when provided withseed rule (i. e. a starting rule) to reduce the burden on experts toconstantly update them.
no code implementations • 31 Jul 2017 • Prutha Date, Ashwinkumar Ganesan, Tim Oates
Convolutional Neural Networks have been highly successful in performing a host of computer vision tasks such as object recognition, object detection, image segmentation and texture synthesis.
no code implementations • 13 Jun 2017 • Mandar Haldekar, Ashwinkumar Ganesan, Tim Oates
Traditional approaches to building a large scale knowledge graph have usually relied on extracting information (entities, their properties, and relations between them) from unstructured text (e. g. Dbpedia).