Shankar Kumar
30 papers · 2002–2025 · 5 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (41) π Academic Marathon Β· Ultra π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Gold π£ Hot Topic Early Bird
π§¬
Topic Evolution
π€
Dynamic Duo
(11)
π
Keyword Champion
(2)
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(83)
Top co-authors
Research topics
Keywords
grammatical error correction
(7)
language model
(4)
transfer learning
(4)
synthetic data generation
(3)
text generation
(3)
beam search
(3)
softmax layer
(2)
speech recognition
(2)
text simplification
(2)
word error rate
(2)
model compression
(2)
large language model
(2)
knowledge distillation
(2)
sequence-to-sequence model
(2)
round-trip translation
(2)
neural machine translation
(1)
style transfer
(1)
language model adaptation
(1)
domain adaptation
(1)
model quantization
(1)
Papers
The Role of Outgoing Connection Heterogeneity in Feedforward Layers of Large Language Models
EMNLP 2025
Synthetic Data Generation for Low-resource Grammatical Error Correction with Tagged Corruption Models
NAACL 2024
Towards an On-device Agent for Text Rewriting
NAACL 2024
Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models
EMNLP 2023
Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR
Interspeech 2023
Conciseness: An Overlooked Language Task
EMNLP 2022
Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES
NAACL 2022
Scaling Language Model Size in Cross-Device Federated Learning
ACL 2022
Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition
Interspeech 2022
Text Generation with Text-Editing Models
NAACL 2022
Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models
ACL 2022
Data Strategies for Low-Resource Grammatical Error Correction
EACL 2021
Lookup-Table Recurrent Language Models for Long Tail Speech Recognition
Interspeech 2021
Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models
EACL 2021
Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus
Interspeech 2020
Seq2Edits: Sequence Transduction Using Span-level Edit Operations
EMNLP 2020
Corpora Generation for Grammatical Error Correction
NAACL 2019
Approaches for Neural-Network Language Model Adaptation
Interspeech 2017
NN-Grams: Unifying Neural Network and n-Gram Language Models for Speech Recognition
Interspeech 2016
Multilingual Open Relation Extraction Using Cross-lingual Projection
NAACL 2015
Expected Sequence Similarity Maximization
NAACL 2010
Model Combination for Machine Translation
NAACL 2010
Efficient Minimum Error Rate Training and Minimum Bayes-Risk Decoding for Translation Hypergraphs and Lattices
ACL 2009
Lattice Minimum Bayes-Risk Decoding for Statistical Machine Translation
EMNLP 2008
Improving Word Alignment with Bridge Languages
EMNLP 2007
Local Phrase Reordering Models for Statistical Machine Translation
EMNLP 2005
A Smorgasbord of Features for Statistical Machine Translation
NAACL 2004
Minimum Bayes-Risk Decoding for Statistical Machine Translation
NAACL 2004
A Weighted Finite State Transducer Implementation of the Alignment Template Model for Statistical Machine Translation
NAACL 2003
Minimum Bayes-Risk Word Alignments of Bilingual Texts
EMNLP 2002