Search Results for author: Vineet Kumar

Found 13 papers, 3 papers with code

Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs

no code implementations20 May 2023 Yatin Nandwani, Vineet Kumar, Dinesh Raghu, Sachindra Joshi, Luis A. Lastras

PMI quantifies the extent to which the document influences the generated response -- with a higher PMI indicating a more faithful response.

Response Generation

Siamese based Neural Network for Offline Writer Identification on word level data

no code implementations17 Nov 2022 Vineet Kumar, Suresh Sundaram

These features are then passed through a deep Convolutional Neural Network (CNN) in which the weights are learned by applying the concept of Similarity learning using Siamese network.

Handwriting Recognition

SEMI-FND: Stacked Ensemble Based Multimodal Inference For Faster Fake News Detection

no code implementations17 May 2022 Prabhav Singh, Ridam Srivastava, K. P. S. Rana, Vineet Kumar

Further, we also report a reduction in the number of parameters used in training when compared to recent relevant works.

Fake News Detection

Gaining Insights into Unrecognized User Utterances in Task-Oriented Dialog Systems

no code implementations11 Apr 2022 Ella Rabinovich, Matan Vetzler, David Boaz, Vineet Kumar, Gaurav Pandey, Ateret Anaby-Tavor

The rapidly growing market demand for automatic dialogue agents capable of goal-oriented behavior has caused many tech-industry leaders to invest considerable efforts into task-oriented dialog systems.

Goal-Oriented Dialog

Offline Text-Independent Writer Identification based on word level data

no code implementations21 Feb 2022 Vineet Kumar, Suresh Sundaram

These key points are then passed through a trained CNN network to generate feature maps corresponding to a convolution layer.

Fairness for AUC via Feature Augmentation

no code implementations24 Nov 2021 Hortense Fong, Vineet Kumar, Anay Mehrotra, Nisheeth K. Vishnoi

We evaluate fairAUC on synthetic and real-world datasets and find that it significantly improves AUC for the disadvantaged group relative to benchmarks maximizing overall AUC and minimizing bias between groups.


Spatial Distribution of Supply and the Role of Market Thickness: Theory and Evidence from Ride Sharing

no code implementations12 Aug 2021 Soheil Ghili, Vineet Kumar

This paper studies the effects of economies of density in transportation markets, focusing on ridesharing.

Predominant Musical Instrument Classification based on Spectral Features

1 code implementation30 Nov 2019 Karthikeya Racharla, Vineet Kumar, Chaudhari Bhushan Jayant, Ankit Khairkar, Paturu Harish

This work aims to examine one of the cornerstone problems of Musical Instrument Retrieval (MIR), in particular, instrument classification.

Classification Clustering +4

Exemplar Encoder-Decoder for Neural Conversation Generation

no code implementations ACL 2018 P, Gaurav ey, Danish Contractor, Vineet Kumar, Sachindra Joshi

In this paper we present the Exemplar Encoder-Decoder network (EED), a novel conversation model that learns to utilize \textit{similar} examples from training data to generate responses.


Lexicon Infused Phrase Embeddings for Named Entity Resolution

no code implementations WS 2014 Alexandre Passos, Vineet Kumar, Andrew McCallum

Most state-of-the-art approaches for named-entity recognition (NER) use semi supervised information in the form of word clusters and lexicons.

Entity Resolution Learning Word Embeddings +3

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