no code implementations • 16 Apr 2024 • Moghis Fereidouni, A. B. Siddique
This work focuses on training smaller language models as agents across various scenarios, systematically evaluating the impact of human demonstrations on the training process.
no code implementations • 28 Mar 2023 • Adib Mosharrof, M. H. Maqbool, A. B. Siddique
To overcome this challenge, we introduce a novel Zero-Shot generalizable end-to-end Task-oriented Dialog system, ZS-ToD, that leverages domain schemas to allow for robust generalization to unseen domains and exploits effective summarization of the dialog history.
no code implementations • 24 Mar 2023 • Adib Mosharrof, Moghis Fereidouni, A. B. Siddique
Phase one acquires two sets of complementary pseudo labels automatically.
no code implementations • 24 Mar 2023 • A. B. Siddique, M. H. Maqbool, Kshitija Taywade, Hassan Foroosh
In this work, we propose a novel framework, P-ToD, to personalize task-oriented dialog systems capable of adapting to a wide range of user profiles in an unsupervised fashion using a zero-shot generalizable reward function.
no code implementations • 12 Mar 2023 • M. H. Maqbool, Umar Farooq, Adib Mosharrof, A. B. Siddique, Hassan Foroosh
To facilitate research for app recommendation systems, we introduce a large-scale dataset, called MobileRec.
no code implementations • 1 Apr 2022 • Ayesha S. Dina, A. B. Siddique, D. Manivannan
Many of these researchers used datasets collected by various organizations to train ML models for predicting intrusions.
no code implementations • 4 Feb 2021 • A. B. Siddique, Fuad Jamour, Luxun Xu, Vagelis Hristidis
Thus, these models should seamlessly adapt and classify utterances with both seen and unseen intents -- unseen intents emerge after deployment and they do not have training data.
no code implementations • 16 Jan 2021 • A. B. Siddique, Fuad Jamour, Vagelis Hristidis
Thus, it is imperative that these models seamlessly adapt and fill slots from both seen and unseen domains -- unseen domains contain unseen slot types with no training data, and even seen slots in unseen domains are typically presented in different contexts.
no code implementations • 31 Jul 2020 • Umar Farooq, A. B. Siddique, Fuad Jamour, Zhijia Zhao, Vagelis Hristidis
Solving the challenge by simply building a model per app (i. e., training with review-response pairs of a single app) may be insufficient because individual apps have limited review-response pairs, and such pairs typically lack the relevant information needed to respond to a new review.
no code implementations • 5 Jul 2020 • A. B. Siddique, Samet Oymak, Vagelis Hristidis
Our evaluation also shows that PUP achieves a great trade-off between semantic similarity and diversity of expression.