Johns Hopkins is launching a wide-ranging, cross-disciplinary effort to tackle health equity challenges across the globe, with grants of up to $25,000 up for grabs starting this summer.

The Alliance for a Healthier World aims to engage experts and students from every corner of Johns Hopkins—in not only research but other partnerships both formal and informal. This week’s launch includes a call for proposals for new collaborative projects that aid disadvantaged populations.

The vision is to build up a network for events, mentorships, and shared resources, ultimately fanning out beyond Johns Hopkins to increase fundraising and partnerships with governments, foundations, and corporations.

The alliance’s efforts will focus on four key global health themes:

• Food and nutrition security
• Healthy environments
• Gender equity and justice
• Transformative technologies and institutions

The pilot project planning grants—now open for submissions through July 15, with additional cycles opening in October—adhere to those principles. The alliance is looking for teams of faculty members and students at Hopkins who can research and propose solutions related to the four key themes, in any geographic area.

The teams must cross at least two disciplines, a requirement that encourages non-traditional collaborations. Application materials offer a few concepts for inspiration—solutions related to domestic violence, food and water contamination, or the depletion of forests and wetlands.

Adapted from The Hub.

The students and faculty of CLSP have 8 papers at ACL 2016 in Berlin, and 8 papers at co-located events.

Main conference
Learning Multiview Embeddings of Twitter Users
Adrian Benton, Raman Arora, and Mark Dredze

Morphological smoothing and extrapolation of word embeddings.
Ryan Cotterell, Hinrich Schütze, and Jason Eisner

Phrase Structure Annotation and Parsing for Learner English
Ryo Nagata and Keisuke Sakaguchi

Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning
Nanyun Peng and Mark Dredze

User modeling in language learning with macaronic texts.
Adithya Renduchintala, Rebecca Knowles, Philipp Koehn, and Jason Eisner

Creating interactive macaronic interfaces for language learning.
Adithya Renduchintala, Rebecca Knowles, Philipp Koehn, and Jason Eisner
(Demo paper)

Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality
Keisuke Sakaguchi, Courtney Napoles, Matt Post and Joel Tetreault
(TACL paper)

Modeling the Interpretation of Discourse Connectives by Bayesian Pragmatics
Frances Yung, Kevin Duh, Taku Komura, and Yuji Matsumoto

CoNLL
Analyzing Learner Understanding of Novel L2 Vocabulary
Rebecca Knowles, Adithya Renduchintala, Philipp Koehn and Jason Eisner

Modeling the Usage of Discourse Connectives as Rational Speech Acts
Frances Yung, Kevin Duh, Taku Komura, and Yuji Matsumoto

Workshops
Findings of the 2016 Conference on Machine Translation
Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Aurelie Neveol, Mariana Neves, Martin Popel, Matt Post, Raphael Rubino, Carolina Scarton, Lucia Specia, Marco Turchi, Karin Verspoor and Marcos Zampieri
First Conference on Machine Translation (WMT16)

Quick and Reliable Document Alignment via TF/IDF-weighted Cosine Distance
Christian Buck and Philipp Koehn
First Conference on Machine Translation (WMT16)

Findings of the WMT 2016 Bilingual Document Alignment Shared Task
Christian Buck and Philipp Koehn
First Conference on Machine Translation (WMT16)

The SIGMORPHON 2016 Shared Task—Morphological Reinflection
Ryan Cotterell, Christo Kirov, John Sylak-Glassman, David Yarowsky, Jason Eisner, and Mans Hulden
SIGMORPHON

The JHU Machine Translation Systems for WMT 2016
Shuoyang Ding, Kevin Duh, Huda Khayrallah, Philipp Koehn, and Matt Post
First Conference on Machine Translation (WMT16)

Modeling Selectional Preferences of Verbs and Nouns in String-to-Tree Machine Translation
Maria Nadejde, Alexandra Birch and Philipp Koehn
First Conference on Machine Translation (WMT16)

Guido Zarella

MITRE Corporation

Abstract

Recurrent neural networks are effective tools for processing natural language, and can be trained to perform sequence processing tasks such as translation, classification, language modeling, and paraphrase detection. But despite major gains in the training and application of artificial neural networks, it remains difficult to construct biologically-inspired models of cognition and language understanding. This talk will discuss recent work to bridge the gap between these fields. We will show how deep neural networks are being used to solve language understanding tasks, and demonstrate that many of these networks can be adapted to run on ultra-low power neuromorphic hardware which simulates the spiking of individual neurons. The resulting proof-of-concept, developed in collaboration at the 2015 Telluride Neuromorphic Engineering Workshop, is an interactive embedded system that uses recurrent neural networks to process language while consuming an estimated .00005 watts.

Biography

Guido Zarrella is a Principal Artificial Intelligence Engineer at the MITRE Corporation in Denver, Colorado.  He leads an R&D team pursuing advances in deep learning for language understanding.  He first began building automatic language learning systems at Carnegie Mellon University for his undergraduate research advisor Herbert A. Simon.  His work today still focuses on unsupervised learning of meaning and intent in informal language.

Yan Liu

Assistant Professor

Computer Science Department

Viterbi School of Engineering

University of Southern California

Abstract

Many emerging applications of machine learning involve time series and spatio-temporal data. In this talk, I will discuss a collection of machine learning approaches to effectively analyze and model large-scale time series and spatio-temporal data. Experiment results will be shown to demonstrate the effectiveness of our models in healthcare and climate applications.

Biography

Yan Liu is an assistant professor in the Computer Science Department at the University of Southern California since 2010. Before that, she was a Research Staff Member at IBM Research. She received her M.Sc and Ph.D. degree from Carnegie Mellon University in 2004 and 2007. Her research interest includes developing scalable machine learning and data mining algorithms with applications to social media analysis, computational biology, climate modeling and healthcare analytics. She has received several awards, including NSF CAREER Award, Okawa Foundation Research Award, ACM Dissertation Award Honorable Mention, Best Paper Award in SIAM Data Mining Conference, Yahoo! Faculty Award, IBM Faculty Award and the winner of several data mining competitions such as KDD Cup and INFORMS data mining competition.