Past events

The Minnesota Natural Language Processing (NLP) Seminar is a venue for faculty, postdocs, students, and anyone else interested in theoretical, computational, and human-centric aspects of natural language processing to exchange ideas and foster collaboration. The talks are every other Friday from 12 p.m. - 1 p.m. during the Spring 2022 semester.

This week's speaker, Yoon Kim (MIT), will be giving a talk titled "Efficient Transfer Learning with Large Language Models"

Abstract 

Transfer learning with large pretrained language models is the dominant paradigm in natural language processing. With moderately-sized models (e.g., BERT), transfer learning involves full finetuning to obtain a task-specific model with its own parameters for each task, which makes the approach hard to scale to storage-constrained scenarios. With larger models (e.g., GPT-3), the model is adapted to each task via natural language prompts and thus the pretrained parameters remain fixed. However, few-shot learning capabilities via prompting emerge only when model sizes are large enough, and thus inference remains expensive. This talk explores two approaches for improving the memory- and inference-efficiency of large language models within the transfer learning paradigm. For finetuned models, we show that only a small subset of the model parameters (0.5%) need to be updated to match the performance of fully-finetuned models. For prompted models, we show that co-training (wherein two models are trained on confidently-labeled outputs from each other) can produce much smaller models that outperform the original prompted model.

Biography

Yoon Kim is an assistant professor at MIT in the Department of Electrical Engineering and Computer Science. He obtained his PhD from Harvard University, where he was advised by Alexander Rush.

Final exams for spring 2022 will be held between Thursday, May 5 and Wednesday, May 11.

Monday, May 3 and Tuesday, May 4 are study days.

View the full academic schedule on One Stop.
 

The last day of instruction for the spring 2022 semester is Monday, May 2.

View the full academic schedule on One Stop.
 

RSVP Link

Our Graduate Student Graduation Celebration event will be held Friday, April 29th from 9:00 - 11:00 (remarks from the department at 10:00 am) held in the University of Minnesota Recreation and Wellness Center Beacon Room on the second floor. Please RSVP as soon as possible. You’re invited if you’re a graduate of our Computer Science, Data Science, or Bioinformatics and Computational Biology graduate program between Summer 2021 through Fall 2022. 

Caps and gowns are optional for our departmental event. We recommend dressing nicely if you plan on attending without a cap and gown. Masking is strongly recommended for the event but is no longer required. Light food and refreshments will be provided.

Note this is not the commencement ceremony this is a social gathering for graduates of CS&E programs only. The commencement ceremony will be at 12 pm in Mariucci the same day.

ASE Graduate Commencement Ceremony

ASE Graduate Commencement for 2022 is also Friday, April 29th starting at noon located at 3M Arena at Mariucci. Information detailing the Graduate Commencement event

Other helpful links:

UMN Bookstore Graduation Link

The Minnesota Natural Language Processing (NLP) Seminar is a venue for faculty, postdocs, students, and anyone else interested in theoretical, computational, and human-centric aspects of natural language processing to exchange ideas and foster collaboration. The talks are every other Friday from 12 p.m. - 1 p.m. during the Fall 2021 semester.

This week's speaker, Greta Tuckute (MIT), will be giving a talk titled "Investigating language in the brain using artificial neural networks."

Abstract

The human language system allows us to infer meaning from text and speech. The unique human ability to comprehend language depends on a left-lateralized fronto-temporal brain network that responds robustly and selectively to linguistic input. A big open question in cognitive science and neuroscience concerns the organization of the language system. Until recently, we had no computationally precise models that could serve as quantitative hypotheses for how core aspects of language might be implemented in the mind and brain. However, artificial neural networks (ANNs) for language have suddenly achieved impressive performance on a wide range of language tasks – prompting the question of whether ANNs can serve as the first computationally precise models of how the human brain may solve the same tasks. 
In my talk, I will discuss: i) ANNs as models of sensory systems, ii) Methodological approaches and assumptions underlying the use of ANNs as models of language processing, iii) Findings from a large-scale investigation1 of 43 diverse ANN language models as models of human neural (fMRI/ECoG) and behavioral responses. In brief, we found that match-to-brain correlated with next-word prediction performance of ANNs (but not performance on other GLUE benchmarks) and we thus claim that a drive to predict future inputs may shape human language processing.

Schrimpf, M., Blank, I.A., Tuckute, G., Kauf, C., Hosseini, E.A., Kanwisher, N.G., Tenenbaum, J.B., & Fedorenko, E. (2021). The neural architecture of language: Integrative modeling converges on predictive processing. Proceedings of the National Academy of Sciences, 118.

Biography

Greta Tuckute is a PhD student in Brain and Cognitive sciences at MIT working with Dr. Ev Fedorenko. She obtained her BSc and MSc degrees from University of Copenhagen in Denmark. She is now working in the intersection of neuroscience and AI, and is interested in exploiting artificial neural networks to understand how language is processed in the mind and brain.

The Minnesota Natural Language Processing (NLP) Seminar is a venue for faculty, postdocs, students, and anyone else interested in theoretical, computational, and human-centric aspects of natural language processing to exchange ideas and foster collaboration. The talks are every other Friday from 12 p.m. - 1 p.m. during the Spring 2022 semester.

This week's speaker, He He (NYU), will be giving a talk titled "Reliable and Factual Natural Language Generation"

Abstract 

Recent advances in large-scale neural language models have transformed the field of text generation, including applications like dialogue and document summarization. Despite human-like fluency, the generated text tends to contain incorrect, inconsistent, or hallucinated information, which hinders the deployment of text generation models in real applications. I will review observations of such errors in current generation tasks, explain challenges in evaluating and mitigating factual errors, and describe our recent attempts on addressing these problems. I will conclude with a discussion on future challenges and directions.

Biography

He He is an assistant professor at the Center for Data Science and the Department of Computer Science at New York University. Before joining NYU, she spent a year at Amazon Web Services and was a postdoc at Stanford University. She received her PhD from University of Maryland, College Park. She is interested in building trustworthy NLP systems in human-centered applications. Her current research focuses on text generation, dialogue systems, and robust language understanding.

Join fellow alumni and friends to learn how University of Minnesota researchers are advancing the theory and practice of human-centered and social computing by experimenting with systems that impact the lives of real people. During this virtual panel, Computer Science & Engineering faculty from the GroupLens lab will give an overview of current research directions that they are most excited about, including:
- Using Human-Centered Machine Learning to identify dangerous health behaviors in online communities
- Understanding the nature of social support in online health communities, and creating techniques to enable more and better support
- Creating novel systems for supporting children’s social connections in family and school contexts
- Personalization in recommender systems; designing recommender systems to serve the needs of multiple stakeholders
- How bulk email is flooding organizations, and what to do about it
- How to make video conference meetings more effective and equitable.

Following a brief presentation on their thoughts on these topics, the panelists will open the floor for general Q&A.

The last day to cancel full semester classes without college approval and receive a "W" is Monday, March 28.

View the full academic schedule on One Stop.
 

The computer science colloquium takes place on Mondays and Fridays from 11:15 a.m. - 12:15 p.m.

This week's speaker, Dakuo Wang (IBM), will be giving a talk titled "Designing Human-Centered AI Systems for Human-AI Collaboration".

Abstract

Human-Centered AI (HCAI) refers to the research effort that aims to design and implement AI techniques to support various human tasks, while taking human needs into consideration and preserving human control. Prior work has focused on human-AI interaction design and explainable AI research (XAI). But, why do some human-centered AI systems work, and some not? In this talk, I show how we can learn from human-human collaboration to design and build AI systems for human-AI collaboration. This work serves as a cornerstone towards the ultimate goal of Human-AI Collaboration, where AI and humans can take complementary and indispensable roles to achieve a better outcome and experience. 

Biography

Dakuo Wang is a Research Staff Member at IBM Research, Principal Investigator at MIT-IBM Watson AI Lab, and Adjunct Professor at Northeastern University. His research lies at the intersection of human-computer interaction (HCI), artificial intelligence (AI), and computer-supported team collaboration (CSCW), with a focus on the exploration, development, and evaluation of human-centered AI (HCAI) systems. The overarching research goal is to democratize AI for every person and every organization, so that they can easily access AI and collaborate with AI to accomplish real-world tasks better -- the “human-AI collaboration” paradigm. Before joining IBM Research, Dakuo got his Ph.D. from the University of California Irvine (“how people write together now” co-advised by Judith Olson and Gary Olson). He has worked as a designer, researcher, and engineer in the U.S., China, and France. He has served in various organizing committees, program committees, and editorial boards for conferences and journals, and ACM has recognized him as an ACM Distinguished Speaker.

The Minnesota Natural Language Processing (NLP) Seminar is a venue for faculty, postdocs, students, and anyone else interested in theoretical, computational, and human-centric aspects of natural language processing to exchange ideas and foster collaboration. The talks are every other Friday from 12 p.m. - 1 p.m. during the Spring 2022 semester.

This week's speaker, Dan Goldwasser (Purdue University), will be giving a talk titled "Neuro-Symbolic Modeling of Text and Social Context"

Abstract 

Understanding natural language communication often requires context, such as the speakers' backgrounds and social conventions, however, when it comes to computationally modeling these interactions, we typically ignore their broader context and analyze the text in isolation. In this talk, I will review on-going work demonstrating the importance of holistically modeling behavioral, social, and textual information. I will focus on several NLP problems, including political discourse analysis on Twitter and partisan news detection, and discuss how jointly modeling text and social behavior can help reduce the supervision effort and provide a better representation for language understanding tasks.

Biography

Dan Goldwasser is an Associate Professor at the Department of Computer Science at Purdue University. He is broadly interested in connecting natural language with real world scenarios and using them to guide natural language understanding. His current interests focus on grounding political discourse to support understanding real-world scenarios, using neuro-symbolic representations. Dan Completed his PhD in Computer Science at the University of Illinois at Urbana-Champaign and was a postdoctoral researcher at the University of Maryland. He has received research support from the NSF, including a recent CAREER award, DARPA and Google.