I have been developing novel solutions to real world problems in both industry and academic settings for over a decade. I am currently a Senior Artificial Intelligence / Machine Learning (AI/ML) Engineer at Apple, where I develop machine learning solutions for text-to-speech to enable Siri voices. I have previously worked at Johns Hopkins University (where I also completed my PhD), MIT Lincoln Laboratory, and Rincon Research Corporation on topics including machine translation (MT), bitext curation and filtering, automatic MT evaluation, multilingual modeling, paraphrasing, cross-language information retrieval, domain adaptation, and digital signal processing.
I developed Vecalign for the ParaCrawl parallel data acquisition project.
Vecalign is an accurate sentence alignment algorithm based on multilingual sentence embeddings
which is linear in complexity with respect to the number of sentences being aligned.
In conjunction with LASER,
Vecalign makes it easy to perform sentence alignment in about 100 languages (i.e. 100^2 language pairs),
without the need for a machine translation system or lexicon.
At the time of writing, Vecalign has the best reported performance on the test set
released with Bleualign.
I also developed Prism,
an automatic MT metric which uses a sequence-to-sequence paraphraser
to score MT system outputs conditioned on their respective human references.
Prism uses a multilingual neural MT model as a zero-shot paraphraser,
which eliminates the need for synthetic paraphrase data and results in a single model which works in many languages (we release a model in 39 languages).
At the time of publication, Prism outperformed or statistically tied with
all metrics submitted to the WMT 2019 metrics shared task
at segment-level human correlation.
I developed bitext filtering code to preprocess the data used to train Prism, but the code is general enough to use for any MT training and is released here.
The Johns Hopkins University
PhD, Computer Science, Center for Language and Speech Processing (CLSP)
Work completed while I was a Research Scientist at the JHU Human Language Technology Center of Excellence (HLTCOE)
I was advised by Philipp Koehn and funded by a National Defense Science and Engineering Graduate (NDSEG) Fellowship
California Institute of Technology
MS, Electrical Engineering
Rose-Hulman Institute of Technology
BS, Electrical Engineering
Improving Arabic Diacritization by Learning to Diacritize and Translate
Brian Thompson and Ali Alshehri
arXiv preprint
[pdf] [bib]
Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversity
Brian Thompson and Matt Post
WMT 2020
[github] [pdf] [bib]
Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing
Brian Thompson and Matt Post
EMNLP 2020
[github] [pdf] [bib]
Exploiting Sentence Order in Document Alignment
Brian Thompson and Philipp Koehn
EMNLP 2020
[pdf] [bib]
Simulated Multiple Reference Training Improves Low-Resource Machine Translation
Huda Khayrallah, Brian Thompson, Matt Post, and Philipp Koehn
EMNLP 2020
[github] [pdf] [bib]
ParaCrawl: Web-Scale Acquisition of Parallel Corpora
Marta Bañón,
Pinzhen Chen,
Barry Haddow,
Kenneth Heafield,
Hieu Hoang,
Miquel Esplà-Gomis,
Mikel Forcada,
Amir Kamran,
Faheem Kirefu,
Philipp Koehn,
Sergio Ortiz-Rojas,
Leopoldo Pla,
Gema Ramírez-Sánchez,
Elsa Sarrías,
Marek Strelec,
Brian Thompson,
William Waites,
Dion Wiggins, and
Jaume Zaragoza
ACL 2020
[website] [pdf] [bib]
Benchmarking Neural and Statistical Machine Translation on Low-Resource African Languages
Kevin Duh, Paul McNamee, Matt Post, and Brian Thompson
Proceedings of The 12th Language Resources and Evaluation Conference (LREC 2020)
[pdf] [bib]
Vecalign: Improved Sentence Alignment in Linear Time and Space
Brian Thompson and Philipp Koehn
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
[github] [pdf] [bib]
HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation
Brian Thompson, Rebecca Knowles, Xuan Zhang, Huda Khayrallah, Kevin Duh, and Philipp Koehn
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
[dataset] [pdf] [bib]
Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation
Brian Thompson, Jeremy Gwinnup, Huda Khayrallah, Kevin Duh, and Philipp Koehn
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) 2019
[pdf] [bib]
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
Brian Thompson, Huda Khayrallah, Antonios Anastasopoulos, Arya D. McCarthy, Kevin Duh, Rebecca Marvin, Paul McNamee, Jeremy Gwinnup, Tim Anderson, and Philipp Koehn
Proceedings of the Third Conference on Machine Translation (WMT) 2018
[pdf] [bib]
Regularized Training Objective for Continued Training for Domain Adaptation in Neural Machine Translation
Huda Khayrallah, Brian Thompson, Kevin Duh, and Philipp Koehn
Proceedings of the Workshop on Neural Machine Translation (WNMT) 2018
[pdf] [bib]
The JHU Machine Translation Systems for WMT 2018
Philipp Koehn, Kevin Duh, and Brian Thompson
Proceedings of the Third Conference on Machine Translation (WMT) 2018: Shared Task Papers
[pdf] [bib]
The AFRL-MITLL WMT17 Systems: Old, New, Borrowed, BLEU
Jeremy Gwinnup, Timothy Anderson, Grant Erdmann, Katherine Young, Michaeel Kazi, Elizabeth Salesky, Brian Thompson, and Jonathan Taylor
Proceedings of the Second Conference on Machine Translation (WMT) 2017
[pdf] [bib]
Implicitly-Defined Neural Networks for Sequence Labeling
Michaeel Kazi and Brian Thompson
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL) 2017
[pdf] [bib]
The MITLL-AFRL IWSLT 2016 Systems
Michaeel Kazi, Elizabeth Salesky, Brian Thompson, Jonathan Taylor, Jeremy Gwinnup, Timothy Anderson, Grant Erdmann, Eric Hansen, Brian Ore, Katherine Young, and Michael Hutt
Proceedings of the ninth International Workshop on Spoken Language Translation (IWSLT) 2016
[pdf] [bib]
The AFRL-MITLL WMT16 News-Translation Task Systems
Jeremy Gwinnup, Tim Anderson, Grant Erdmann, Katherine Young, Michaeel Kazi, Elizabeth Salesky, and Brian Thompson
Proceedings of the First Conference on Machine Translation (WMT) 2016
[pdf] [bib]
The MITLL-AFRL IWSLT 2015 System
Michaeel Kazi, Brian Thompson, Elizabeth Salesky, Timothy Anderson, Grant Erdmann, Eric Hansen, Brian Ore, Katherine Young, Jeremy Gwinnup, Michael Hutt, and Christina May
Proceedings of the International Workshop on Spoken Language Translation (IWSLT) 2015
[pdf] [bib]
The AFRL-MITLL WMT15 System: There’s More than One Way to Decode It!
Jeremy Gwinnup, Tim Anderson, Grant Erdmann, Katherine Young, Christina May, Michaeel Kazi, Elizabeth Salesky, and Brian Thompson
Proceedings of the Tenth Workshop on Statistical Machine Translation (WMT) 2015
[pdf] [bib]
The MITLL-AFRL IWSLT 2014 MT System
Michaeel Kazi, Elizabeth Salesky, Brian Thompson, Jessica Ray, Michael Coury, Wade Shen, Tim Anderson, Grant Erdmann, Jeremy Gwinnup, Katherine Young, Brian Ore and Michael Hutt
Proceedings of the International Workshop on Spoken Language Translation (IWSLT) 2014
[pdf] [bib]