Mihir Kale
9 papers · 2020–2023 · 4 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (23) 🐣 Hot Topic Early Bird 👥 Mega-Team · Legion
❓
The Questioner
Venues
Top co-authors
Research topics
Natural Language Processing
(6)
Generation
(5)
Deep Learning
(4)
Resources & Methods
(4)
Artificial Intelligence
(3)
Learning Types · Deep Learning
(3)
Machine Learning
(2)
Applications
(2)
Core AI
(2)
Speech & Audio
(1)
Architectures
(1)
Core Methods
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Recognition
(1)
Keywords
natural language generation
(4)
dialogue system
(2)
benchmark evaluation
(2)
transfer learning
(2)
multilingual nlp
(1)
speech recognition
(1)
few-shot learning
(1)
parallel data
(1)
linguistic annotation
(1)
task-oriented dialogue
(1)
compositional generalization
(1)
language model
(1)
pre-trained model
(1)
evaluation metric
(1)
linguistic representation
(1)
human evaluation
(1)
cross-lingual transfer
(1)
named entity
(1)
machine translation
(1)
representation learning
(1)
Papers
XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages
EMNLP 2023
CLSE: Corpus of Linguistically Significant Entities
EMNLP 2022
Improving Compositional Generalization with Self-Training for Data-to-Text Generation
ACL 2022
XTREME-S: Evaluating Cross-lingual Speech Representations
Interspeech 2022
mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer
NAACL 2021
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?
ACL 2021
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
ACL 2021
TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems
ACL 2021
Template Guided Text Generation for Task-Oriented Dialogue
EMNLP 2020