Search Results for author: Vivek Subramanian

Found 7 papers, 1 papers with code

Debiasing Gender Bias in Information Retrieval Models

no code implementations2 Aug 2022 Dhanasekar Sundararaman, Vivek Subramanian

We definitively show that pre-trained models for IR do not perform well in zero-shot retrieval tasks when full fine-tuning of a large pre-trained BERT encoder is performed and that lightweight fine-tuning performed with adapter networks improves zero-shot retrieval performance almost by 20% over baseline.

Cultural Vocal Bursts Intensity Prediction Information Retrieval +1

Improving Downstream Task Performance by Treating Numbers as Entities

no code implementations7 May 2022 Dhanasekar Sundararaman, Vivek Subramanian, Guoyin Wang, Liyan Xu, Lawrence Carin

Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed.

Classification Question Answering

SpanPredict: Extraction of Predictive Document Spans with Neural Attention

no code implementations NAACL 2021 Vivek Subramanian, Matthew Engelhard, Sam Berchuck, Liqun Chen, Ricardo Henao, Lawrence Carin

In many natural language processing applications, identifying predictive text can be as important as the predictions themselves.

Descriptive

Graph Convolutional Networks Reveal Neural Connections Encoding Prosthetic Sensation

no code implementations23 Aug 2020 Vivek Subramanian, Joshua Khani

Extracting stimulus features from neuronal ensembles is of great interest to the development of neuroprosthetics that project sensory information directly to the brain via electrical stimulation.

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