Image of fall foliage on campus.

Brown Bag Talks

[Supported by the U.S. National Science Foundation: Grant No. 1048406]

The purpose of the group is to discuss issues in large datasets, language and speech processing. We are hoping to bring our cross-disciplinary strengths to these areas, to share ideas, to discuss the current state of the art, and to collaborate on research topics.

Upcoming Brown Bag Talks

WHEN: Wednesday, February 14th, 4-5 p.m.
WHERE: Schmitt Hall, room 104 or, join us via Zoom: https://montclair.zoom.us/s/83293152236

Tal Linzen, PhD, Associate Professor of Linguistics and Data Science at NYU, Research Scientist at Google
How much data do neural networks need for syntactic generalization?

I will discuss work that examines the syntactic generalization capabilities of contemporary neural network models such as transformers. When trained from scratch to perform tasks such transforming a declarative sentence to a question, models generalize in ways that are very different from humans. Following self-supervised pre-training (word prediction), however, transformers generalize in line with syntactic structure. Robust syntactic generalization emerges only after exposure to a very large amount of data, but even more moderate amounts of pre-training data begin to steer the models away from their linear inductive biases. Perhaps surprisingly, pre-training on simpler child-directed speech is more data-efficient than on other genres; at the same time, this bias is insufficient for a transformer to learn to form questions correctly just from the data available in child-directed speech.

Bio: Tal Linzen is an Associate Professor of Linguistics and Data Science at New York University and a Research Scientist at Google. Before moving to NYU in 2020, he was a faculty member at Johns Hopkins University, and before that, a postdoctoral researcher at the École Normale Supérieure in Paris. He received his PhD from NYU in 2015. At NYU, he directs the Computation and Psycholinguistics Lab, which studies the connections between machine learning and human language comprehension and acquisition. He has received a Google Faculty Award and a National Science Foundation CAREER award.

Past Events

Monday, December 4, 1-2 p.m.
Mike Kalfus, GrapheneAI, Chief Commercial Officer
Artificial Intelligence in Healthcare Analytics: What is it good for? Absolute Everything….Say It Again!

Monday, November 13, 1-4pm
Anastassia Loukina, PhD, Engineering Manager, Grammarly
“How do we evaluate AI systems in real-world applications?”

Thursday, October 19, 4:00 – 5:00pm
Nick Williams, Instructional Specialist, Montclair State University
Why Documenting Languages (still) Matters and How to Do It

Thursday, September 28, 4:00 – 5:00pm
Adam Jardine, Associate Professor, Rutgers University
Why Computational Learning Theory Matters for Language Learning

Thursday, May 4, 3:45 – 5:00pm
Computational Lingustics students, Educational Testing Service
Educational Testing Service (ETS) Internship Presentations

Thursday, March 16th, 2023
Liubou Shefarevich, Second Language Testing Inc., a Berlitz company
Applying coursework in linguistics to an obscure field of language assessment, or what you can do with your linguistics degree

Thursday February 23, 2023
4:00PM – 5:00PM Zoom
Dr. Michael Flor, Educational Testing Service
AIG for Idioms: Towards testing knowledge of English idiomatic expressions with automatic item generation

Tuesday November 23, 2021
1:00PM – 2:00PM Zoom
Andrey Kutuzov, University of Oslo
Grammatical Profiling for Semantic Change Detection

Tuesday October 26th, 2021
4:00PM – 5:00PM Zoom
Anjalie Field, Carnegie Mellon University/University of Washington
Distantly-supervised Language Technologies for Social Text Analysis

Wednesday, May 5, 2021
3:30 – 4:30PM Zoom
Victor Kuperman, McMaster University
What makes us proficient readers in a second language: new eye-tracking corpora

April 6, 2021
4:15 – 5:15PM, Zoom
Dr. Xiao Yang, Language Data Researcher, Amazon Alexa
Linguistics Careers in Tech: What are they and how to prepare for tech job hunting

March 10, 2021
Gary Lupyan, Professor of Psychology at the University of Wisconsin-Madison
Learning from Language: How vocabulary helps to structure the mind

Watch a recording of Gary Lupyan’s March 10 discussion

November 17, 2020
Xiaofei Lu, Department of Linguistics, The Pennsylvania State University
Sense-aware Lexical Sophistication Indicies and Their Relationship to L2 Writing Quality

February 20, 2020
Sara Rosenthal, IBM
NLP for Healthcare in Electronic Health Records and Care Management Notes

November 14, 2019
Dr. Gerard de Melo, Rutgers University
Digging Deeper : Representations for Fine-Grained Affective Text Analysis

November 7, 2019
Zubin Jelveh, Ph.D., Crime Lab New York
Political Language in Economics

April 11, 2019
Chelsey Hill, Assistant Professor of Information Management and Business Analytics, Feliciano School of Business
Brown Bag Talk: Complaint Mining in the Automotive Industry

March 27, 2019
Richard Sproat, Research Scientist, Google Research, New York
Neural Models of Text Normalization for Speech Applications

March 7, 2019
Heng Ji, Rensselaer Polytechnic Institute
Universal Information Extraction

February 13, 2019
Joe Tetreault, Grammarly
It’s a Matter of Style: Experiments in Style Detection and Transformation with Natural Language Processing

View more past Brown Bag Talks here