Patrick Lehnen
7 papers · 2015–2022 · 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 ↑
π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (23) β The Questioner
π
Trend Setter
Top co-authors
Research topics
Machine Learning
(6)
Natural Language Processing
(4)
Learning Types Β· Machine Learning
(4)
Artificial Intelligence
(3)
Application Areas
(3)
Applications
(3)
Core AI
(3)
Deep Learning
(2)
Learning Types Β· Deep Learning
(2)
Reinforcement Learning
(1)
Core Methods
(1)
Generation
(1)
Methods
(1)
Optimization & Theory
(1)
Resources & Methods
(1)
Keywords
spoken language understanding
(4)
dialog system
(3)
data augmentation
(2)
intent classification
(2)
domain adaptation
(1)
multilingual nlp
(1)
speech recognition
(1)
policy learning
(1)
natural language understanding
(1)
paraphrase generation
(1)
distribution drift
(1)
implicit feedback
(1)
model drift
(1)
model deployment
(1)
multi-domain learning
(1)
production system
(1)
regression model
(1)
multilingual model
(1)
distributional drift
(1)
task-oriented dialog
(1)
Papers
Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned?
EMNLP 2022
Feedback Attribution for Counterfactual Bandit Learning in Multi-Domain Spoken Language Understanding
EMNLP 2021
Multilingual Paraphrase Generation For Bootstrapping New Features in Task-Oriented Dialog Systems
EMNLP 2021
Predicting Temporal Performance Drop of Deployed Production Spoken Language Understanding Models
Interspeech 2021
The Impact of Intent Distribution Mismatch on Semi-Supervised Spoken Language Understanding
Interspeech 2021
Leveraging User Paraphrasing Behavior In Dialog Systems To Automatically Collect Annotations For Long-Tail Utterances
COLING 2020
A Comparison of Update Strategies for Large-Scale Maximum Expected BLEU Training
NAACL 2015