no code implementations • 5 Jun 2023 • Aditya Srikanth Veerubhotla, Lahari Poddar, Jun Yin, György Szarvas, Sharanya Eswaran
Self-rationalizing models that also generate a free-text explanation for their predicted labels are an important tool to build trustworthy AI applications.
no code implementations • 25 Oct 2022 • Lahari Poddar, György Szarvas, Cheng Wang, Jorge Balazs, Pavel Danchenko, Patrick Ernst
Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints.
no code implementations • 16 May 2022 • Marin Vlastelica, Patrick Ernst, György Szarvas
Utilizing amortized variational inference for latent-action reinforcement learning (RL) has been shown to be an effective approach in Task-oriented Dialogue (ToD) systems for optimizing dialogue success.
1 code implementation • 27 Dec 2021 • Jiahuan Pei, Cheng Wang, György Szarvas
In this work, we propose a novel way to enable transformers to have the capability of uncertainty estimation and, meanwhile, retain the original predictive performance.
1 code implementation • EMNLP 2020 • Phillip Keung, Yichao Lu, György Szarvas, Noah A. Smith
We present the Multilingual Amazon Reviews Corpus (MARC), a large-scale collection of Amazon reviews for multilingual text classification.
no code implementations • Association for Computational Linguistics 2008 • György Szarvas, Veronika Vincze, Richárd Farkas, János Csirik
This article reports on a corpus annotation project that has produced a freely available resource for research on handling negation and uncertainty in biomedical texts (we call this corpus the BioScope corpus).