MLconf NYC 2019 Speaker Resources

Emily Pitler, Software Engineer, Google AI

Representations from Natural Language Data: Successes and Challenges

Papers

Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. To Appear, NAACL 2019.
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention Is All You Need. NIPS 2017.
Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. Improving Language Understanding by Generative Pre-Training. Preprint, 2018.
Yuan Zhang, Jason Riesa, Daniel Gillick, Anton Bakalov, Jason Baldridge, and David Weiss. A Fast, Compact, Accurate Model for Language Identification of Codemixed Text. EMNLP 2018.
Ali Elkahky, Kellie Webster, Daniel Andor, and Emily Pitler. A Challenge Set and Methods for Noun-Verb Ambiguity. EMNLP 2018.
Kellie Webster, Marta Recasens, Vera Axelrod, and Jason Baldridge. Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns. To appear, TACL 2019.
Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. Natural Questions: a Benchmark for Question Answering Research. To appear, TACL 2019.

Code and Pretrained Models

Datasets:

Tutorials:

View the slides for this presentation.

Watch this presentation on YouTube.

Anna Choromanska, Assistant Professor, NYU Tandon School of Engineering

Data-driven challenges in AI: scale, information selection, and safety

Neel Sundaresan, Partner Director, Microsoft

Teaching a Machine to Code

Esperanz López Aguilera, Machine Learning Team, Kx

Using a Bayesian Neural Network in the Detection of Exoplanets

Soumith Chintala, Researcher, Facebook

Increasing the Impact of AI Through Better Software

Amir Sadoughi, Senior Software Development Engineer, Amazon Web Services

Developing large-scale machine learning algorithms on Amazon SageMaker

Renaud Bourassa, Staff Software Engineer, Slack

Building Machine Learning Models with Strict Privacy Boundaries

Reference- Michael Bendersky, Xuanhui Wang, Donald Metzler, and Marc Najork. 2017. Learning from User Interactions in Personal Search via Attribute Parameterization. In Proceedings of the Tenth ACM International Conference on Web Search and Data Mining (WSDM ’17). ACM, New York, NY, USA, 791-799. DOI: https://doi.org/10.1145/3018661.3018712

Rishabh Mehrotra, Research Scientist, Spotify Research

Recommendations in a Marketplace: Personalizing Explainable Recommendations with Multi-objective Contextual Bandits

Madalina Fiterau , Assistant Professor, University of Massachusetts Amherst

Hybrid Machine Learning Methods for the Interpretation and Integration of Heterogeneous Multimodal Data

UMass Profile page: https://www.cics.umass.edu/people/fiterau-brostean-madalina

Webpage for PhD/Postdoc projects: http://www.cs.cmu.edu/~mfiterau/

Lab and project pages:

References:
[1] Madalina Fiterau and Artur Dubrawski. Projection Retrieval for Classification. In
Advances in Neural Information Processing Systems 25, pages 3032–3040,
NIPS 2012. Poster.
[2] Fiterau M, Dubrawski A, Chen L, Hravnak M, Clermont G, Pinsky MR. Automatic
identification of artifacts in monitoring critically ill patients. Annual Congress of
the European Society of Intensive Care Medicine 2014; 39 Suppl 2: S470.
Electronic Poster.
[3] Donghan Wang, Madalina Fiterau and Artur Dubrawski, VIPR: An Interactive
Tool for Meaningful Visualization of High-Dimensional Data, Demonstration at the
International Joint Conference in Artificial Intelligence IJCAI 2016.
[4] Fiterau M, Wang J, Dubrawski A, Clermont G, Hravnak M, Pinsky MR. Using
expert review to calibrate semi-automated adjudication of vital sign alerts in step-
down units. Society of Critical Care Medicine Annual Congress 2016. Abstract
and slides. Star Research Award.
[5] Peter Kontschieder, Madalina Fiterau, Antonio Criminisi and Samuel Rota-Bulo.
Deep Neural Decision Forests, International Conference in Computer Vision,
ICCV 2015. Spotlight and poster. Marr Prize for Best Paper.
[6] Madalina Fiterau, Suvrat Bhooshan, Jason Fries, Charles Bournhonesque,
Jennifer Hicks, Eni Halilaj, Christopher Ré and Scott Delp. ShortFuse:
Biomedical Time Series Representations in the Presence of Structured
Information. 3rd Conference on Machine Learning for Healthcare, MLHC 2017.
Spotlight.
[7] Jason A Fries, Paroma Varma, Vincent S Chen, Ke Xiao, Heliodoro Tejeda,
Priyanka Saha, Jared Dunnmon, Henry Chubb, Shiraz Maskatia, Madalina
Fiterau, Scott Delp, Euan Ashley, Christopher Ré, James Priest, Weakly
supervised classification of rare aortic valve malformations using unlabeled
cardiac MRI sequences. Accepted to Nature Communications.

Sandhya Prabhakaran, Research Fellow, Memorial Sloan Kettering Cancer Centre

A Bayesian Approach To Model Overlapping Objects Available As Distance Data

A tutorial on Bayesian nonparametric models: http://gershmanlab.webfactional.com/pubs/GershmanBlei12.pdf
Leo Breiman: ‘Statistical Modeling: The Two Cultures’: https://projecteuclid.org/download/pdf_1/euclid.ss/1009213726
An abstract of this work as Spotlight at the Bayesian Nonparametrics Workshop at NeurIPS 2018: https://drive.google.com/file/d/1ExVpeUomv8Z4mPMu5as_CbmrHjVY0IDV/view
Tutorials on latest Deep learning papers: https://www.depthfirstlearning.com/ (@DepthFirstLearn)

Liliana Cruz Lopez, Graduate Student, Columbia University

Deep Reinforcement Learning based Insulin Controller for Effective Type-1 Diabetic Care

Kerry Weinberg, Head of Data Science, Amgen Digital Health

Putting the Tech in Biotech: Challenges and Opportunities in Application of AI in Healthcare

Nitin Sharma, Research Scientist, PayPal

Deep Learning Applications to Online Payment Fraud Detection

Janani Kalyanam, Sr. Data Scientist, Intuit

Machine Learning to Detect Illegal Online Sales of Prescription Opioids

Leanna Kent, Sr. Data Scientist, Elder Research

Using Network Analysis to Detect Kickback Schemes Among Medical Providers

What are kickbacks? https://www.gao.gov/assets/680/674771.pdf
Jaccard Index- https://onlinelibrary.wiley.com/doi/full/10.1002/asi.20732
Egonets- https://us.sagepub.com/sites/default/files/upm-binaries/70890_Crossley___Social_Network_Analysis.pdf
Graphs in R with iGraph- https://igraph.org/r/doc/
Graph metrics- https://www.nas.ewi.tudelft.nl/people/Piet/papers/TUDreport20111111_MetricList.pdf

Niels Bantilan, Machine Learning Engineer, Talkspace

Augmenting Mental Health Care in the Digital Age: Machine Learning as a Therapist Assistant

Related Papers

Kshirsagar, Rohan, Robert Morris, and Sam Bowman. “Detecting and explaining crisis.” arXiv preprint arXiv:1705.09585 (2017).
Al Hanai, Tuka, Mohammad Ghassemi, and James Glass. “Detecting Depression with Audio/Text Sequence Modeling of Interviews.” Proc. Interspeech. 2018.
Fast, Ethan, Binbin Chen, and Michael S. Bernstein. “Empath: Understanding topic signals in large-scale text.” Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems. ACM, 2016.

Github Repos

ELI5 – explaining machine learning models: https://github.com/TeamHG-Memex/eli5
LIME – locally interpretable model-agnostic explanations: https://github.com/marcotcr/lime
Empath: https://github.com/Ejhfast/empath-client