Kyunghyun Cho (New York University): Three recent directions in neural machine translation @ Hackerman Hall, Room B17
Jul 20 @ 10:30 am – 11:30 am

In this talk, I will describe three research problems I have recently worked on and found worth further discussion and investigation in the context of neural machine translation. First, I will discuss whether the standard autoregressive sequence model could be replaced with non-autoregressive one and if so, how we would do so by introducing the idea of iterative refinement for sequence generation. Second, I will introduce one particular type of meta-learning algorithms, called MAML [Finn et al., 2017] and discuss how this is well-suited for multilingual translation and in particular low-resource translation. Lastly, I will quickly discuss slightly old work on real-time translation. All of these works are highly experimental but at the same time extremely fun to think about and discuss.



Kyunghyun Cho is an assistant professor of computer science and data science at New York University and a research scientist at Facebook AI Research. He was a postdoctoral fellow at University of Montreal until summer 2015 under the supervision of Prof. Yoshua Bengio, and received PhD and MSc degrees from Aalto University early 2014 under the supervision of Prof. Juha Karhunen, Dr. Tapani Raiko and Dr. Alexander Ilin. He tries his best to find a balance among machine learning, natural language processing, and life, but almost always fails to do so.

James Foulds (UMBC) “Differential Fairness for Machine Learning and Artificial Intelligence Systems: Unbiased Decisions with Biased Data” @ Hackerman Hall B17
Nov 19 @ 12:00 pm – 1:15 pm


With the rising influence of machine learning algorithms on many important aspects of our daily lives, there are growing concerns that biases inherent in data can lead the behavior of these algorithms to discriminate against certain populations. Biased data can lead data-driven algorithms to produce biased outcomes along lines of gender, race, sexual orientation, and political ties, with important real-world consequences, including decision-making for lending and law enforcement. Thus, there is an urgent need for machine learning algorithms that make unbiased decisions with biased data. We propose a novel framework for measuring and correcting bias in data-driven algorithms, with inspiration from privacy-preserving machine learning and Bayesian probabilistic modeling. A case study on census data demonstrates the utility of our approach.


Dr. James Foulds is an Assistant Professor in the Department of Information Systems at UMBC. His research interests are in both applied and foundational machine learning, focusing on probabilistic latent variable models and the inference algorithms to learn them from data. His work aims to promote the practice of probabilistic modeling for computational social science, and to improve AI’s role in society regarding privacy and fairness. He earned his Ph.D. in computer science at the University of California, Irvine, and was a postdoctoral scholar at the University of California, Santa Cruz, followed by the University of California, San Diego. His master’s and bachelor’s degrees were earned with first class honours at the University of Waikato, New Zealand, where he also contributed to the Weka data mining system.

Andrew Piper (McGill University) ” How can we use machine learning to understand narration?” @ Hackerman Hall B17
Nov 12 @ 12:00 pm – 1:15 pm


Narration is a universal human practice that serves as a key site of education, collective memory, fostering social belief systems, and furthering human creativity. Recent studies in economics (Shiller, 2020), climate science (Bushell et al., 2017), political polarization (Kubin et al., 2021), and mental health (Adler et al., 2016) suggest an emerging interdisciplinary consensus that narrative is a central concept for understanding human behavior and beliefs. For close to half a century, the field of narratology has developed a rich set of theoretical frameworks for understanding narrative. And yet these theories have largely gone untested on large, heterogenous collections of texts. Scholars continue to generate schemas by extrapolating from small numbers of manually observed documents. In this talk, I will discuss how we can use machine learning to develop data-driven theories of narration to better understand what Labov and Waletzky called “the simplest and most fundamental narrative structures.” How can machine learning help us approach what we might call a minimal theory of narrativity?


Andrew Piper is Professor and William Dawson Scholar in the Department of Languages, Literatures, and Cultures at McGill University. He is the director of _.txtlab


a laboratory for cultural analytics, and editor of the /Journal of Cultural Analytics/, an open-access journal dedicated to the computational study of culture. He is the author of numerous books and articles on the relationship of technology and reading, including /Book Was There: Reading in Electronic Times/(Chicago 2012), /Enumerations: Data and Literary Study/(Chicago 2018), and most recently, /Can We Be Wrong? The Problem of Textual Evidence in a Time of Data/(Cambridge 2020).

Ariya Rastrow (Amazon) @ Hackerman Hall B17
Oct 7 @ 12:00 pm – 1:15 pm

Center for Language and Speech Processing