no code implementations • RANLP 2021 • Haytham Elfdaeel, Stanislav Peshterliev
To reduce computational cost and latency, we propose decoupling the transformer MRC model into input-component and cross-component.
no code implementations • 13 Jun 2023 • Xiao Yang, Ahmed K. Mohamed, Shashank Jain, Stanislav Peshterliev, Debojeet Chatterjee, Hanwen Zha, Nikita Bhalla, Gagan Aneja, Pranab Mohanty
Importantly, LEDO is computationally efficient compared to methods that require loss function change, and cost-effective as the resulting data can be used in the same continuous training pipeline for production.
no code implementations • 8 Apr 2020 • Stanislav Peshterliev, Christophe Dupuy, Imre Kiss
Recent attempts to ingest external knowledge into neural models for named-entity recognition (NER) have exhibited mixed results.
no code implementations • 27 Feb 2019 • Stanislav Peshterliev, Alexander Hsieh, Imre Kiss
On public datasets, F10-SGD obtains 22% faster training time compared to FastText for text classification.
no code implementations • NAACL 2019 • Stanislav Peshterliev, John Kearney, Abhyuday Jagannatha, Imre Kiss, Spyros Matsoukas
We explore active learning (AL) for improving the accuracy of new domains in a natural language understanding (NLU) system.
no code implementations • 19 Jul 2018 • Grant P. Strimel, Kanthashree Mysore Sathyendra, Stanislav Peshterliev
In this paper we investigate statistical model compression applied to natural language understanding (NLU) models.
no code implementations • 1 Nov 2017 • Anjishnu Kumar, Arpit Gupta, Julian Chan, Sam Tucker, Bjorn Hoffmeister, Markus Dreyer, Stanislav Peshterliev, Ankur Gandhe, Denis Filiminov, Ariya Rastrow, Christian Monson, Agnika Kumar
This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) a large scale Spoken Language Understanding (SLU) Software Development Kit (SDK) that enables developers to extend the capabilities of Amazon's virtual assistant, Alexa.