Ayush Kumar
21 papers · 2015–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (38) 🏃 Academic Marathon · Half 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🤝
Dynamic Duo
(11)
❓
The Questioner
(4)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🗃️
Keyword Collector
(85)
Top co-authors
Research topics
Natural Language Processing
(16)
Machine Learning
(11)
Applications
(11)
Artificial Intelligence
(8)
Core AI
(6)
Application Areas
(5)
Learning Types · Machine Learning
(5)
Deep Learning
(4)
Generation
(4)
Learning Paradigms
(4)
Learning Types · Deep Learning
(4)
Resources & Methods
(3)
Speech & Audio
(2)
Core Methods
(2)
Recognition
(2)
Keywords
contact center
(4)
domain adaptation
(4)
language model
(3)
few-shot learning
(3)
representation learning
(3)
text classification
(3)
spoken language understanding
(2)
sentiment analysis
(2)
large language model
(2)
call summarization
(2)
speech processing
(2)
automatic speech recognition
(2)
convolutional neural network
(2)
abstractive summarization
(2)
conversational ai
(1)
speech recognition
(1)
data augmentation
(1)
natural language inference
(1)
direct preference optimization
(1)
text summarization
(1)
Papers
Entity Exchange in the Wild: A Diagnostic Study of LLM Based Real-World Conversational Entity Extraction
ACL 2026
PROPEL: Prompt Optimization with Expert Priors for Small and Medium-sized LLMs
NAACL 2025
Spot the BlindSpots: Systematic Identification and Quantification of Fine-Grained LLM Biases in Contact Center Call Summarization
EMNLP 2025
Can probing classifiers reveal the learning by contact center large language models?: No, it doesn’t!
NAACL 2024
The Paradox of Preference: A Study on LLM Alignment Algorithms and Data Acquisition Methods
NAACL 2024
Tweak to Trust: Assessing the Reliability of Summarization Metrics in Contact Centers via Perturbed Summaries
NAACL 2024
COnVoy: A Contact Center Operated Pipeline for Voice of Customer Discovery
Interspeech 2023
Investigating the Role and Impact of Disfluency on Summarization
EMNLP 2023
Listening To Silences In Contact Center Conversations Using Textual Cues
Interspeech 2023
Tailored Real-Time Call Summarization System for Contact Centers
Interspeech 2023
What questions are my customers asking?: Towards Actionable Insights from Customer Questions in Contact Center Calls
Interspeech 2023
Does Utterance entails Intent?: Evaluating Natural Language Inference Based Setup for Few-Shot Intent Detection
Interspeech 2022
Investigating the Characteristics of a Transformer in a Few-Shot Setup: Does Freezing Layers in RoBERTa Help?
EMNLP 2022
Partially Humanizing Weak Supervision: Towards a Better Low Resource Pipeline for Spoken Language Understanding
EMNLP 2022
Real-Time Monitoring of Silences in Contact Center Conversations
Interspeech 2022
PhonemeBERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript
Interspeech 2021
What BERT Based Language Model Learns in Spoken Transcripts: An Empirical Study
EMNLP 2021
BAKSA at SemEval-2020 Task 9: Bolstering CNN with Self-Attention for Sentiment Analysis of Code Mixed Text
SemEval 2020
A Hybrid Deep Learning Architecture for Sentiment Analysis
COLING 2016
IIT-TUDA at SemEval-2016 Task 5: Beyond Sentiment Lexicon: Combining Domain Dependency and Distributional Semantics Features for Aspect Based Sentiment Analysis
SemEval 2016
IITPSemEval: Sentiment Discovery from 140 Characters
SemEval 2015