Isaac Caswell
16 papers · 2019–2025 · 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (26) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🏆
Keyword Champion
👥
Mega-Team · Squad
🔬
Deep Specialist
(13)
🗃️
Keyword Collector
(80)
📈
Trend Setter
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Natural Language Processing
(15)
Applications
(15)
Machine Learning
(10)
Resources & Methods
(9)
Deep Learning
(8)
Learning Types · Deep Learning
(7)
Learning Types · Machine Learning
(6)
Artificial Intelligence
(2)
Application Areas
(2)
Core Methods
(2)
Generation
(2)
Learning Paradigms · Artificial Intelligence
(2)
Models
(2)
Learning Paradigms · Machine Learning
(1)
Optimization & Theory
(1)
Keywords
low-resource language
(6)
neural machine translation
(5)
machine translation
(5)
data selection
(2)
domain adaptation
(2)
curriculum learning
(2)
large language model
(2)
parallel data
(2)
multilingual model
(2)
transfer learning
(2)
multilingual dataset
(2)
translation quality
(2)
language identification
(1)
parallel corpus
(1)
text generation
(1)
benchmark evaluation
(1)
cross-lingual transfer
(1)
language model
(1)
data augmentation
(1)
corpus creation
(1)
Papers
Findings of the WMT 2025 Shared Task of the Open Language Data Initiative
EMNLP 2025
Google Translate’s Research Submission to WMT2025
EMNLP 2025
SMOL: Professionally Translated Parallel Data for 115 Under-represented Languages
EMNLP 2025
Connecting Language Technologies with Rich, Diverse Data Sources Covering Thousands of Languages
COLING 2024
GATITOS: Using a New Multilingual Lexicon for Low-resource Machine Translation
EMNLP 2023
MADLAD-400: A Multilingual And Document-Level Large Audited Dataset
NeurIPS 2023
Separating the Wheat from the Chaff with BREAD: An open-source benchmark and metrics to detect redundancy in text
EMNLP 2023
XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages
EMNLP 2023
BLEU might be Guilty but References are not Innocent
EMNLP 2020
Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus
COLING 2020
Learning a Multi-Domain Curriculum for Neural Machine Translation
ACL 2020
Translationese as a Language in “Multilingual” NMT
ACL 2020
APE at Scale and Its Implications on MT Evaluation Biases
ACL 2019
Dynamically Composing Domain-Data Selection with Clean-Data Selection by “Co-Curricular Learning” for Neural Machine Translation
ACL 2019
Investigating Multilingual NMT Representations at Scale
EMNLP 2019
Tagged Back-Translation
ACL 2019