Mitesh Khapra
17 papers · 2010–2024 · 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (46) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Gold π£ Hot Topic Early Bird
π§
Keyword Pioneer
π₯
Mega-Team Β· Squad
π
Renaissance Researcher
(6)
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(71)
Top co-authors
Research topics
Natural Language Processing
(9)
Artificial Intelligence
(7)
Deep Learning
(7)
Machine Learning
(7)
Resources & Methods
(6)
Applications
(5)
Core AI
(5)
Learning Types Β· Machine Learning
(5)
Architectures
(4)
Learning Types Β· Deep Learning
(4)
Core Methods
(3)
Generation
(3)
Learning Paradigms
(3)
Speech & Audio
(2)
Recognition
(2)
Keywords
indian language
(3)
low-resource language
(3)
transfer learning
(3)
self-supervised learning
(2)
speech dataset
(2)
text generation
(2)
multilingual speech
(2)
sign language recognition
(2)
multilingual model
(2)
cross-lingual transfer
(2)
pre-trained model
(2)
automatic speech recognition
(2)
indic language
(2)
speech processing
(1)
model robustness
(1)
neural machine translation
(1)
natural language generation
(1)
text classification
(1)
self-attention mechanism
(1)
natural language understanding
(1)
Papers
How Good is Zero-Shot MT Evaluation for Low Resource Indian Languages?
ACL 2024
IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
NeurIPS 2024
IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages
ACL 2024
Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users
EMNLP 2023
Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons
ACL 2022
Addressing Resource Scarcity across Sign Languages with Multilingual Pretraining and Unified-Vocabulary Datasets
NeurIPS 2022
IndicBART: A Pre-trained Model for Indic Natural Language Generation
ACL 2022
Input-specific Attention Subnetworks for Adversarial Detection
ACL 2022
OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages
ACL 2022
ElimiNet: A Model for Eliminating Options for Reading Comprehension with Multiple Choice Questions
IJCAI 2018
On Controllable Sparse Alternatives to Softmax
NeurIPS 2018
An Autoencoder Approach to Learning Bilingual Word Representations
NeurIPS 2014
Claims on demand β an initial demonstration of a system for automatic detection and polarity identification of context dependent claims in massive corpora
COLING 2014
All Words Domain Adapted WSD: Finding a Middle Ground between Supervision and Unsupervision
ACL 2010
CFILT: Resource Conscious Approaches for All-Words Domain Specific WSD
SemEval 2010
OWNS: Cross-lingual Word Sense Disambiguation Using Weighted Overlap Counts and Wordnet Based Similarity Measures
SemEval 2010
Value for Money: Balancing Annotation Effort, Lexicon Building and Accuracy for Multilingual WSD
COLING 2010