Search Results for author: Arvind Agarwal

Found 11 papers, 3 papers with code

Towards Automated Evaluation of Explanations in Graph Neural Networks

no code implementations22 Jun 2021 Vanya BK, Balaji Ganesan, Aniket Saxena, Devbrat Sharma, Arvind Agarwal

Explaining Graph Neural Networks predictions to end users of AI applications in easily understandable terms remains an unsolved problem.

VeeAlign: Multifaceted Context Representation using Dual Attention for Ontology Alignment

1 code implementation EMNLP 2021 Vivek Iyer, Arvind Agarwal, Harshit Kumar

Ontology Alignment is an important research problem applied to various fields such as data integration, data transfer, data preparation, etc.

Anomaly Detection

Multifaceted Context Representation using Dual Attention for Ontology Alignment

no code implementations16 Oct 2020 Vivek Iyer, Arvind Agarwal, Harshit Kumar

Ontology Alignment is an important research problem that finds application in various fields such as data integration, data transfer, data preparation etc.

A Practical Dialogue-Act-Driven Conversation Model for Multi-Turn Response Selection

no code implementations IJCNLP 2019 Harshit Kumar, Arvind Agarwal, Sachindra Joshi

This paper proposes an end-to-end multi-task model for conversation modeling, which is optimized for two tasks, dialogue act prediction and response selection, with the latter being the task of interest.

Compliance Change Tracking in Business Process Services

no code implementations20 Aug 2019 Srikanth G Tamilselvam, Ankush Gupta, Arvind Agarwal

Compliance officers responsible for maintaining adherence constantly struggle to keep up with the large amount of changes in regulatory requirements.

Classification General Classification

Dialogue-act-driven Conversation Model : An Experimental Study

no code implementations COLING 2018 Harshit Kumar, Arvind Agarwal, Sachindra Joshi

The utility of additional semantic information for the task of next utterance selection in an automated dialogue system is the focus of study in this paper.

Dialogue Generation

Multitask Learning for Sequence Labeling Tasks

no code implementations25 Apr 2014 Arvind Agarwal, Saurabh Kataria

Our method learns multiple models, one model for each label sequence.

Learning Multiple Tasks using Manifold Regularization

no code implementations NeurIPS 2010 Arvind Agarwal, Samuel Gerber, Hal Daume

We present a novel method for multitask learning (MTL) based on {\it manifold regularization}: assume that all task parameters lie on a manifold.

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