Thibault Sellam
10 papers · 2020–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (19) π£ Hot Topic Early Bird π Conference Polyglot (4)
π
Cross-Pollinator
(3)
π
Renaissance Researcher
(5)
π₯
Mega-Team
(56)
π
Century Club
(10)
Conferences
ACL (4)
EMNLP (4)
ICLR (1)
IJCNLP (1)
Top co-authors
Keywords
evaluation metric
(3)
automated metric
(2)
text generation evaluation
(2)
human judgment correlation
(2)
human evaluation
(2)
natural language generation
(2)
transfer learning
(1)
knowledge distillation
(1)
machine translation
(1)
multilingual nlp
(1)
neural machine translation
(1)
text generation
(1)
summarization evaluation
(1)
semantic matching
(1)
probabilistic framework
(1)
semantic similarity
(1)
reward hacking
(1)
language model
(1)
multilingual evaluation
(1)
multilingual model
(1)
Papers
Dialect-robust Evaluation of Generated Text
ACL 2023
SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation
EMNLP 2023
Reward Gaming in Conditional Text Generation
ACL 2023
The MultiBERTs: BERT Reproductions for Robustness Analysis
ICLR 2022
Learning Compact Metrics for MT
EMNLP 2021
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
ACL 2021
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
IJCNLP 2021
Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task
EMNLP 2020
A Multilingual View of Unsupervised Machine Translation
EMNLP 2020
BLEURT: Learning Robust Metrics for Text Generation
ACL 2020