Programs & Events

programs

YINS Summer Seminar: Eric Feltham

“Observational Learning: background and proposed novel experimental design”

Speaker: Eric Feltham
Human Nature Lab, YINS

Talk Summary: I will discuss a proposal for a novel experiment design to study social learning, based on previous paradigms from individual learning Daw et al. (2011) and Dawson and Foss (1965). Further, I will give a general literature review on social learning. At this early stage, I am looking for feedback on the design and technical approach in addition to general comments.

YINS Co-directors Daniel Spielman & Nicholas Christakis

Christakis and Spielman made Sterling Professors

Anonymous
July 23, 2018

The Sterling Professorship is the highest honor bestowed on Yale faculty, upon approval by the Yale Board of Trustees. Two of the four Sterling Professors announced this month, Daniel A. Spielman and Nicholas A. Christakis co-direct the interdisciplinary Yale Institute for Network Science.  

Daniel A. Spielman, newly named as Sterling Professor of Computer Science, focuses his research on the design and analysis of algorithms, network science, machine learning, digital communications, and scientific computing.

Nicholas A. Christakis, a sociologist and physician who conducts research in the areas of network science, biosocial science, and public health, was named as Sterling Professor of Social and Natural Science.

Daniel A. Spielman

Spielman’s work helped revolutionize the field of error-correcting codes, which allow communication devices to transmit information even if part of it is corrupted. That work has made communication faster and more reliable and has been used for broadcasting high-definition television. In 2013, he and two collaborators solved the Kadison-Singer conjecture, a problem that had gone unsolved by mathematicians for more than 50 years. Its solution, scientists believe, could have significant implications for the field of statistics.A 1992 summa cum laude graduate of Yale, where he earned exceptional distinction in computer science and received the Beckwith Prize in mathematics, Spielman received his Ph.D. at the Massachusetts Institute of Technology. He served as an assistant and associate professor of applied mathematics at MIT before joining the Yale faculty in 2006 as professor of applied mathematics and computer science. Prior to his new appointment, he served as the Henry Ford II Professor of Computer Science.

Spielman has been recognized with numerous awards and honors for his scholarly contributions. In 2013, he received a MacArthur Fellowship, popularly known as the “genius” grant, from the John D. and Catherine T. MacArthur Foundation. He was awarded the 2010 Rolf Nevanlinna Prize from the International Mathematical Union, the 2009 Fulkerson Prize, and, on two occasions, the Gödel Prize for outstanding papers in the area of theoretical computer science.  He is a member of the National Academy of Sciences.

Nicholas A. Christakis

Dr. Nicholas A. Christakis has been named as Sterling Professor of Social and Natural Science at Yale. He is a sociologist and physician who conducts research in the areas of network science, biosocial science, and public health.

The Sterling Professorship is the highest honor bestowed on Yale faculty, upon approval by the Yale Board of Trustees.

“I am deeply honored by this recognition,” Christakis said, “which reflects Yale’s substantial commitment to inter-disciplinary science and also the vibrant contributions of the many students and scholars on my research team. I am eager to make myself useful to Yale’s mission.”

Christakis directs the Human Nature Lab and is co-director of the Yale Institute for Network Science, which explores fundamental properties of social, biological, engineering, and computational networks, and invents approaches to intervene in them for the better.

Christakis’ research program includes large-scale randomized trials to improve maternal and child health in developing countries (such as Honduras and India), as well as basic science experiments exploring human social interactions, social genomics, the microbiome, and artificial intelligence.

A graduate of Yale College in 1984, Christakis received his M.D. from Harvard Medical School, his M.P.H. from the Harvard School of Public Health, and his Ph.D. from the University of Pennsylvania. At Yale, Christakis has appointments in the Departments of Sociology, Medicine, Ecology and Evolutionary Biology, Biomedical Engineering, and Statistics and Data Science, as well as at the School of Management. Before joining the Yale faculty in 2013, Christakis served as professor at Harvard University for 12 years.  Prior to that, he was on the faculty at the University of Chicago, where he was also a clinical director of a hospice program delivering end-of-life care to underserved populations.

Christakis is the author of several books, including “Death Foretold: Prophecy and Prognosis in Medical Care” and “Connected: The Surprising Power of Our Social Networks and How They Shape Our Lives,” which has been translated into 20 languages.  His new book, “Blueprint: The Evolutionary Origins of a Good Society,” will appear in early 2019. He has also written more than 180 peer-reviewed articles in professional journals.

Christakis was elected to the Institute of Medicine of the National Academy of Sciences in 2006; the American Association for the Advancement of Science in 2010; and the American Academy of Arts and Sciences in 2017. In 2009, he was named by Time magazine to its annual list of the 100 most influential people in the world.

External link: 
LILY Lab Logo

A very successful research year for the Natural Language Processing group at Yale

Anonymous
June 7, 2018

The LILY (Language, Information, and Learning at Yale) Lab so far this year has published eight papers on Natural Language Processing (NLP) at three top-tier conferences: AAAI (The Association for the Advancement of Artificial Intelligence), NAACL (North American Chapter of the Association for Computational Linguistics) and ACL (Association for Computational Linguistics). These publications are the result of collaboration among the PhD students in the LILY lab as well as over a dozen Yale undergraduates and master’s students.

One of the papers, “TutorialBank: A Manually-Collected Corpus for Prerequisite Chains, Survey Extraction and Resource Recommendation” by Alexander R. Fabbri, Irene Li, Prawat Trairatvorakul, Yijiao He, Wei Tai Ting, Robert Tung, Caitlin Westerfield and Dragomir R. Radev will appear at ACL, the top venue in NLP, in July in Melbourne, Australia. This paper aims to facilitate NLP research and education through a dataset of over 7,500 hand-curated resources about NLP and related fields such as Information Retrieval, Machine Learning and Artificial Intelligence as well as an internally-maintained catalog and search engine named AAN.

AAN (short for “All About NLP”) allows users to browse resources according to a taxonomy of over 300 topics which was developed by LILY. Users can also find tutorials, surveys and other educational materials relevant to a given project given a query consisting of a title and an abstract. More information about the search engine and other features of AAN can be found on this blog post.

The other published papers focus on natural language dialogue, translating sentences to database queries as well as part-of-speech tagging, text summarization and Tree Adjoining Grammar parsing. Here is the full list of papers.

  1. TutorialBank: A Manually-Collected Corpus for Prerequisite Chains, Survey Extraction and Resource Recommendation by Alexander R. Fabbri, Irene Li, Prawat Trairatvorakul, Yijiao He, Wei Tai Ting, Robert Tung, Caitlin Westerfield and Dragomir R. Radev
  2. Improving Text-to-SQL Evaluation Methodology by Catherine Finegan-Dollak, Jonathan K. Kummerfeld, Li Zhang, Karthik Ramanathan, Sesh Sadasivam, Rui Zhang and Dragomir Radev
  3. Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering by Rui Zhang, Cicero Nogueira dos Santos, Michihiro Yasunaga, Bing Xiang and Dragomir Radev
  4. TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation by Tao Yu, Zifan Li, Zilin Zhang, Rui Zhang and Dragomir Radev
  5. Robust Multilingual Part-of-Speech Tagging via Adversarial Training by Michihiro Yasunaga, Jungo Kasai and Dragomir Radev
  6. End-to-end Graph-based TAG Parsing with Neural Networks by Jungo Kasai, Robert Frank, Pauli Xu, William Merrill and Owen Rambow
  7. Sentence Ordering using Recurrent Neural Networks by Lajanugen Logeswaran, Honglak Lee and Dragomir Radev
  8. Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs by Rui Zhang, Honglak Lee, Lazaros Polymenakos and Dragomir Radev

Pages

Subscribe to programs