Dan Garrette - Natural Language Processing & Machine Learning
Dan Garrette
I am a Research Scientist at
Google DeepMind
in New York. My research focuses on
Natural
Language Processing
and
Machine Learning
I completed my Ph.D. in
Computer Science at
The University of Texas at Austin
in 2015 and
was later a postdoc in
the University of Washington
Curriculum Vitae (pdf)
Email:
dhgarrette@gmail.com
Selected Publications
Low-Resource Machine Learning for NLP
-->
How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning
Rochelle Choenni,
Dan Garrette
, and
Ekaterina Shutova
EMNLP 2023  
Character-Aware Models Improve Visual Text Rendering
Rosanne Liu*,
*,
Chitwan Saharia,
William Chan,
Adam Roberts,
Sharan Narang,
Irina Blok,
RJ Mical,
Mohammad Norouzi, and
Noah Constant*
ACL 2023  
[slides]
[poster]
Cross-Lingual Transfer with Language-Specific Subnetworks for Low-Resource Dependency Parsing
Computational Linguistics, 2023  
FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation
Parker Riley,
Timothy Dozat,
Jan A. Botha,
Xavier Garcia,
Jason Riesa,
Orhan Firat, and
Noah Constant
TACL 2023  
CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation
Jonathan H. Clark,
Iulia Turc, and
John Wieting
TACL 2022  
Frequency Effects on Syntactic Rule Learning in Transformers
Jason Wei
Tal Linzen
Ellie Pavlick
EMNLP 2021  
[blog]
Improving Multilingual Models with Language-Clustered Vocabularies
Hyung Won Chung,
Kiat Chuan Tan, and
Jason Riesa
EMNLP 2020  
TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages
Eunsol Choi,
Michael Collins,
Tom Kwiatkowski,
Vitaly Nikolaev,
Jennimaria Palomaki
TACL 2020  
How multilingual is Multilingual BERT?
Telmo Pires,
Eva Schlinger, and
ACL 2019  
[slides.pdf]
[talk video]
Part-of-Speech Tagging for Code-Switched, Transliterated Texts without Explicit Language Identification
Kelsey Ball
EMNLP 2018  
[code]
Automatic Compositor Attribution in the First Folio of Shakespeare
Maria Ryskina
Hannah Alpert-Abrams
Taylor Berg-Kirkpatrick
ACL 2017  
An Unsupervised Model of Orthographic Variation for Historical Document Transcription
NAACL 2016  
[data]
[slides.key]
A Supertag-Context Model for Weakly-Supervised CCG Parser Learning
Chris Dyer
Jason Baldridge
Noah A. Smith
CoNLL 2015  
Unsupervised Code-Switching for Multilingual Historical Document Transcription
Dan Klein
NAACL 2015  
Weakly-Supervised Grammar-Informed Bayesian CCG Parser Learning
AAAI 2015  
Weakly-Supervised Bayesian Learning of a CCG Supertagger
CoNLL 2014  
Real-World Semi-Supervised Learning of POS-Taggers for Low-Resource Languages
Jason Mielens
ACL 2013  
Learning a Part-of-Speech Tagger from Two Hours of Annotation
NAACL 2013  
[commentary]
*Best Talk Award
Finalist
Commentary
Hal Daume -
My NAACL 2013 list...
Daniel Marcu -
NLP Trends - NAACL 2013
140 Characters or less -
[1]
[2]
[3]
[4]
[5]
[6]
[7]
[8]
A Formal Approach to Linking Logical Form and Vector-Space Lexical Semantics
Katrin Erk
Raymond Mooney
In: Harry Bunt, Johan Bos, and Stephen Pulman (eds)
Computing Meaning, Vol. 4
, 2013
Montague Meets Markov: Deep Semantics with Probabilistic Logical Form
Islam Beltagy, Cuong Chau,
Gemma Boleda
*SEM 2013
Type-Supervised Hidden Markov Models for POS Tagging with Incomplete Tag Dictionaries
EMNLP 2012  
Integrating Logical Representations with Probabilistic Information using Markov Logic
International Conference on Computational Semantics, 2011
An Extensible Toolkit for Computational Semantics
Ewan Klein
International Conference on Computational Semantics, 2009
Design by Kristin Serna