Search Results for author: Ayush Kumar

Found 23 papers, 3 papers with code

What BERT Based Language Model Learns in Spoken Transcripts: An Empirical Study

no code implementations EMNLP (BlackboxNLP) 2021 Ayush Kumar, Mukuntha Narayanan Sundararaman, Jithendra Vepa

We probe BERT based language models (BERT, RoBERTa) trained on spoken transcripts to investigate its ability to understand multifarious properties in absence of any speech cues.

Language Modelling Spoken Language Understanding

Towards Probing Contact Center Large Language Models

no code implementations26 Dec 2023 Varun Nathan, Ayush Kumar, Digvijay Ingle, Jithendra Vepa

Additionally, we compare the performance of OOB-LLMs and CC-LLMs on the widely used SentEval dataset, and assess their capabilities in terms of surface, syntactic, and semantic information through probing tasks.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization

no code implementations24 May 2023 Aman Priyanshu, Supriti Vijay, Ayush Kumar, Rakshit Naidu, FatemehSadat Mireshghallah

More specifically, we find that when ChatGPT is prompted to summarize cover letters of a 100 candidates, it would retain personally identifiable information (PII) verbatim in 57. 4% of cases, and we find this retention to be non-uniform between different subgroups of people, based on attributes such as gender identity.

In-Context Learning

Malaria detection using Deep Convolution Neural Network

no code implementations4 Mar 2023 Sumit Kumar, Harsh Vardhan, Sneha Priya, Ayush Kumar

The latest WHO report showed that the number of malaria cases climbed to 219 million last year, two million higher than last year.

Deep Learning Driven Natural Languages Text to SQL Query Conversion: A Survey

no code implementations8 Aug 2022 Ayush Kumar, Parth Nagarkar, Prabhav Nalhe, Sanjeev Vijayakumar

Even if numerous deep learning-based algorithms are proposed or studied, there still is very challenging to have a generic model to solve the data query issues using natural language in a real-work scenario.

Decision Making Text-To-SQL

An Open Source Interactive Visual Analytics Tool for Comparative Programming Comprehension

no code implementations29 Jul 2022 Ayush Kumar, Ashish Kumar, Aakanksha Prasad, Michael Burch, Shenghui Cheng, Klaus Mueller

We illustrate the usefulness of our tool by applying it to the eye movements of 216 programmers of multiple expertise levels that were collected during two code comprehension tasks.

Eye Gaze Estimation Model Analysis

no code implementations28 Jul 2022 Aveena Kottwani, Ayush Kumar

We explore techniques for eye gaze estimation using machine learning.

Gaze Estimation

Low Resource Pipeline for Spoken Language Understanding via Weak Supervision

no code implementations21 Jun 2022 Ayush Kumar, Rishabh Kumar Tripathi, Jithendra Vepa

In Weak Supervised Learning (WSL), a model is trained over noisy labels obtained from semantic rules and task-specific pre-trained models.

Emotion Classification Few-Shot Learning +3

Exploring the Limits of Natural Language Inference Based Setup for Few-Shot Intent Detection

1 code implementation14 Dec 2021 Ayush Kumar, Vijit Malik, Jithendra Vepa

Our method achieves state-of-the-art results on 1-shot and 5-shot intent detection task with gains ranging from 2-8\% points in F1 score on four benchmark datasets.

Few-Shot Learning Generalized Few-Shot Learning +5

What BERT Based Language Models Learn in Spoken Transcripts: An Empirical Study

no code implementations19 Sep 2021 Ayush Kumar, Mukuntha Narayanan Sundararaman, Jithendra Vepa

We probe BERT based language models (BERT, RoBERTa) trained on spoken transcripts to investigate its ability to understand multifarious properties in absence of any speech cues.

Spoken Language Understanding

Investigating Bias In Automatic Toxic Comment Detection: An Empirical Study

no code implementations14 Aug 2021 Ayush Kumar, Pratik Kumar

Finally, in effort to mitigate bias in toxicity detection models, a multi-task setup trained with auxiliary task of toxicity sub-types proved to be useful leading to upto 0. 26% (6% relative) gain in AUC scores.

Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript

1 code implementation1 Feb 2021 Mukuntha Narayanan Sundararaman, Ayush Kumar, Jithendra Vepa

In this work, we propose a BERT-style language model, referred to as PhonemeBERT, that learns a joint language model with phoneme sequence and ASR transcript to learn phonetic-aware representations that are robust to ASR errors.

intent-classification Intent Classification +1

Machine Learning-Based Early Detection of IoT Botnets Using Network-Edge Traffic

no code implementations22 Oct 2020 Ayush Kumar, Mrinalini Shridhar, Sahithya Swaminathan, Teng Joon Lim

The detection performance is also shown to be robust to an increase in the number of IoT devices connected to the edge gateway where EDIMA is deployed.

BIG-bench Machine Learning Traffic Classification

BAKSA at SemEval-2020 Task 9: Bolstering CNN with Self-Attention for Sentiment Analysis of Code Mixed Text

1 code implementation SEMEVAL 2020 Ayush Kumar, Harsh Agarwal, Keshav Bansal, Ashutosh Modi

Sentiment Analysis of code-mixed text has diversified applications in opinion mining ranging from tagging user reviews to identifying social or political sentiments of a sub-population.

General Classification Opinion Mining +1

Gated Mechanism for Attention Based Multimodal Sentiment Analysis

no code implementations21 Feb 2020 Ayush Kumar, Jithendra Vepa

Multimodal sentiment analysis has recently gained popularity because of its relevance to social media posts, customer service calls and video blogs.

Multimodal Sentiment Analysis

A Secure Contained Testbed for Analyzing IoT Botnets

no code implementations17 Jun 2019 Ayush Kumar, Teng Joon Lim

A DETERlab-based IoT botnet testbed is presented in this work.

Cryptography and Security Networking and Internet Architecture

OCR++: A Robust Framework For Information Extraction from Scholarly Articles

no code implementations COLING 2016 Singh Mayank, Barua Barnopriyo, Palod Priyank, Garg Manvi, Satapathy Sidhartha, Bushi Samuel, Ayush Kumar, Rohith Krishna Sai, Gamidi Tulasi, Goyal Pawan, Mukherjee Animesh

This paper proposes OCR++, an open-source framework designed for a variety of information extraction tasks from scholarly articles including metadata (title, author names, affiliation and e-mail), structure (section headings and body text, table and figure headings, URLs and footnotes) and bibliography (citation instances and references).

Optical Character Recognition (OCR)

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