Search Results for author: Raghav Gupta

Found 19 papers, 8 papers with code

AnyTOD: A Programmable Task-Oriented Dialog System

no code implementations20 Dec 2022 Jeffrey Zhao, Yuan Cao, Raghav Gupta, Harrison Lee, Abhinav Rastogi, Mingqiu Wang, Hagen Soltau, Izhak Shafran, Yonghui Wu

We propose AnyTOD, an end-to-end, zero-shot task-oriented dialog (TOD) system capable of handling unseen tasks without task-specific training.

Benchmarking Language Modelling

Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue

no code implementations8 Apr 2022 Raghav Gupta, Harrison Lee, Jeffrey Zhao, Abhinav Rastogi, Yuan Cao, Yonghui Wu

Building universal dialogue systems that operate across multiple domains/APIs and generalize to new ones with minimal overhead is a critical challenge.

Dialogue State Tracking Zero-shot Generalization

Description-Driven Task-Oriented Dialog Modeling

1 code implementation21 Jan 2022 Jeffrey Zhao, Raghav Gupta, Yuan Cao, Dian Yu, Mingqiu Wang, Harrison Lee, Abhinav Rastogi, Izhak Shafran, Yonghui Wu

Task-oriented dialogue (TOD) systems are required to identify key information from conversations for the completion of given tasks.

dialog state tracking

Galaxy Morphology Classification using Neural Ordinary Differential Equations

1 code implementation14 Dec 2020 Raghav Gupta, P. K. Srijith, Shantanu Desai

We introduce a continuous depth version of the Residual Network (ResNet) called Neural ordinary differential equations (NODE) for the purpose of galaxy morphology classification.

Instrumentation and Methods for Astrophysics Astrophysics of Galaxies

Schema-Guided Dialogue State Tracking Task at DSTC8

2 code implementations2 Feb 2020 Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, Pranav Khaitan

The goal of this task is to develop dialogue state tracking models suitable for large-scale virtual assistants, with a focus on data-efficient joint modeling across domains and zero-shot generalization to new APIs.

Data Augmentation Dialogue State Tracking +1

Extremely Small BERT Models from Mixed-Vocabulary Training

no code implementations EACL 2021 Sanqiang Zhao, Raghav Gupta, Yang song, Denny Zhou

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint.

Knowledge Distillation Language Modelling +2

Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset

4 code implementations12 Sep 2019 Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, Pranav Khaitan

In this work, we introduce the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains.

Dialogue State Tracking Response Generation +2

Robust Zero-Shot Cross-Domain Slot Filling with Example Values

1 code implementation ACL 2019 Darsh J Shah, Raghav Gupta, Amir A Fayazi, Dilek Hakkani-Tur

Task-oriented dialog systems increasingly rely on deep learning-based slot filling models, usually needing extensive labeled training data for target domains.

slot-filling Zero-shot Slot Filling

Multi-task learning for Joint Language Understanding and Dialogue State Tracking

no code implementations WS 2018 Abhinav Rastogi, Raghav Gupta, Dilek Hakkani-Tur

This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems.

Dialogue State Tracking Multi-Task Learning +1

An Efficient Approach to Encoding Context for Spoken Language Understanding

no code implementations1 Jul 2018 Raghav Gupta, Abhinav Rastogi, Dilek Hakkani-Tur

In task-oriented dialogue systems, spoken language understanding, or SLU, refers to the task of parsing natural language user utterances into semantic frames.

Computational Efficiency Spoken Language Understanding +1

Optimal Cost Almost-sure Reachability in POMDPs

no code implementations14 Nov 2014 Krishnendu Chatterjee, Martin Chmelík, Raghav Gupta, Ayush Kanodia

We consider partially observable Markov decision processes (POMDPs) with a set of target states and every transition is associated with an integer cost.

Cannot find the paper you are looking for? You can Submit a new open access paper.