Midwest Speech and Language Days (MSLD) is a two-day meeting that continues the tradition of Illinois Speech Day and the Midwest Computational Linguistics Colloquium. Presenters and attendees from all Midwest universities and research institutions are invited. The goal is to increase awareness of speech and language research going on in the region and to foster collaboration among sites.

Dates and Locations

MSLD 2025 will be held on April 15–16, 2025 at the University of Notre Dame, Notre Dame, Indiana, in McKenna Hall in the Reyes Family Boardroom.

Schedule

Tuesday April 15

• 08:00–09:00 Breakfast (provided) and registration
• 09:00–09:05 Welcome
• 09:05–10:00 Keynote: Karen Livescu, Toyota Technological Institute at Chicago
• 10:00–10:15 Break
• 10:15–11:00 Talk Session 1 (Chair: Bang Nguyen)
• 11:00–11:15 Break
• 11:15–12:00 Talk Session 2 (Chair: Yining Lu)
• 12:00–13:00 Lunch (provided)
• 13:00–14:00 Poster Session 1 (Chair: Ken Sible)
• 14:00–14:45 Talk Session 3 (Chair: Aarohi Srivastava)
• 14:45–15:00 Break
• 15:00–16:00 Poster Session 2 (Chair: Stephen Bothwell)
• 16:00–16:55 Keynote: Heng Ji, University of Illinois at Urbana–Champaign

Wednesday April 16

• 08:00–09:00 Breakfast (provided) and registration
• 09:00–09:05 Announcements
• 09:05–10:00 Keynote: David Mortensen, Carnegie Mellon University
• 10:00–10:15 Break
• 10:15–11:00 Talk Session 4 (Chair: Andy Yang)
• 11:15–12:00 Talk Session 5 (Chair: Katsumi Ibaraki)
• 12:00–13:00 Lunch (provided)
• 13:00–14:00 Poster Session 3 (Chair: Ken Sible)
• 14:00–14:55 Keynote: Mohit Bansal, University of North Carolina at Chapel Hill
• 14:55–15:00 Closing

Poster Printing

Thank you to the Navari Family Center for Digital Scholarship (NFCDS) for providing complimentary poster printing.

If you had submitted your poster by April 7th, you will be able to pick up your poster at the conference venue.

Keynote Speakers

• 
  
  Mohit Bansal (UNC Chapel Hill)
  Trustworthy Planning Agents for Collaborative Reasoning and Multimodal Generation
  Bio Abstract

Dr. Mohit Bansal is the John R. & Louise S. Parker Distinguished Professor and the Director of the MURGe-Lab (UNC-NLP Group) in the Computer Science department at UNC Chapel Hill. He received his PhD from UC Berkeley in 2013 and his BTech from IIT Kanpur in 2008. His research expertise is in natural language processing and multimodal machine learning, with a particular focus on multimodal generative models, grounded and embodied semantics, reasoning and planning agents, faithful language generation, and interpretable, efficient, and generalizable deep learning. He is a AAAI Fellow and recipient of the Presidential Early Career Award for Scientists and Engineers (PECASE), IIT Kanpur Young Alumnus Award, DARPA Director's Fellowship, NSF CAREER Award, Google Focused Research Award, Microsoft Investigator Fellowship, Army Young Investigator Award (YIP), DARPA Young Faculty Award (YFA), and outstanding paper awards at ACL, CVPR, EACL, COLING, CoNLL, and TMLR. He has been a keynote speaker for the AACL 2023, CoNLL 2023, and INLG 2022 conferences. His service includes EMNLP and CoNLL Program Co-Chair, and ACL Executive Committee, ACM Doctoral Dissertation Award Committee, ACL Americas Sponsorship Co-Chair, and Associate/Action Editor for TACL, CL, IEEE/ACM TASLP, and CSL journals. Webpage: https://www.cs.unc.edu/~mbansal/

In this talk, I will present our journey of developing trustworthy and adaptive AI planning agents that can reliably communicate and collaborate for uncertainty-calibrated reasoning (on math, commonsense, coding, tool use, etc.) as well as for interpretable, controllable multimodal generation (across text, images, videos, audio, layouts, etc.). In the first part, we will discuss how to teach agents to be trustworthy and reliable collaborators via social/pragmatic multi-agent interactions (e.g., confidence calibration via speaker-listener reasoning and learning to balance positive and negative persuasion), as well as how to acquire and improve agent skills needed for efficient and robust perception and action (e.g., learning reusable, verified abstractions over actions & code, and adaptive data generation based on discovered weak skills). In the second part, we will discuss interpretable and controllable multimodal generation via LLM-agents based planning and programming, such as layout-controllable image generation and evaluation via visual programming (VPGen, VPEval, DSG), consistent video generation via LLM-guided multi-scene planning, targeted corrections, and retrieval-augmented motion adaptation (VideoDirectorGPT, VideoRepair, DreamRunner), and interactive and composable any-to-any multimodal generation (CoDi, CoDi-2).

• 
  
  Heng Ji (University of Illinois at Urbana-Champaign)
  AI plays medicinal chemist and material scientist
  Bio Abstract

Heng Ji is a Tenured Full Professor and Associate Director for Research of Siebel School of Computing and Data Science, and a faculty member affiliated with Electrical and Computer Engineering Department, Coordinated Science Laboratory, and Carl R. Woese Institute for Genomic Biology of University of Illinois Urbana-Champaign. She is an Amazon Scholar. She is the Founding Director of Amazon-Illinois Center on AI for Interactive Conversational Experiences (AICE). She received her B.A. and M. A. in Computational Linguistics from Tsinghua University, and her M.S. and Ph.D. in Computer Science from New York University. Her research interests focus on Natural Language Processing, especially on Multimedia Multilingual Information Extraction, Knowledge-enhanced Large Language Models and Vision-Language Models, and AI for Science. The awards she received include Outstanding Paper Award at ACL2024, two Outstanding Paper Awards at NAACL2024, "Young Scientist" by the World Laureates Association in 2023 and 2024, "Young Scientist" and a member of the Global Future Council on the Future of Computing by the World Economic Forum in 2016 and 2017, "Women Leaders of Conversational AI" (Class of 2023) by Project Voice, "AI's 10 to Watch" Award by IEEE Intelligent Systems in 2013, NSF CAREER award in 2009, PACLIC2012 Best paper runner-up, "Best of ICDM2013" paper award, "Best of SDM2013" paper award, ACL2018 Best Demo paper nomination, ACL2020 Best Demo Paper Award, NAACL2021 Best Demo Paper Award, Google Research Award in 2009 and 2014, IBM Watson Faculty Award in 2012 and 2014 and Bosch Research Award in 2014-2018. She was invited to testify to the U.S. House Cybersecurity, Data Analytics, & IT Committee as an AI expert in 2023. She was selected to participate in DARPA AI Forward in 2023. She was invited by the Secretary of the U.S. Air Force and AFRL to join Air Force Data Analytics Expert Panel to inform the Air Force Strategy 2030, and invited to speak at the Federal Information Integrity R&D Interagency Working Group (IIRD IWG) briefing in 2023. She is the lead of many multi-institution projects and tasks, including the U.S. ARL projects on information fusion and knowledge networks construction, DARPA ECOLE MIRACLE team, DARPA KAIROS RESIN team and DARPA DEFT Tinker Bell team. She has coordinated the NIST TAC Knowledge Base Population task 2010-2020. She served as the associate editor for IEEE/ACM Transaction on Audio, Speech, and Language Processing, and the Program Committee Co-Chair of many conferences including NAACL-HLT2018 and AACL-IJCNLP2022. She was elected as the North American Chapter of the Association for Computational Linguistics (NAACL) secretary 2020-2023. Her research has been widely supported by the U.S. government agencies (DARPA, NSF, DoE, ARL, IARPA, AFRL, DHS) and industry (Amazon, Google, Bosch, IBM, Disney).

There exist approximately 166 billion small molecules, with 970 million deemed druglike. Similarly there is a vast pool of molecule candidates for new materials. This scarcity underscores the urgent need for innovative approaches, calling upon the NLP community to contribute significantly to medicine and material science. However, the challenges are manifold. Existing large language models (LLMs) alone are insufficient due to their tendency to generate erroneous claims confidently (hallucinate). Moreover, traditional knowledge bases do not adequately address the issue. This gap persists because chemistry language diverges significantly from natural language, demanding specialized domain knowledge, multimodal information integration, and long context understanding. Using drug discovery, personalized drug synergy, and material discovery as case studies, I will present our approaches to tackle these challenges and turn an AI agent into a Medicinal Chemist or Material Scientist. I will share preliminary results from animal testing conducted on drug variants, and newly discovered material variants for efficient Organic Photovoltaic Devices proposed by AI algorithms. Furthermore, I advocate for a paradigm shift towards ‘slow science’, emphasizing the integration of feedback loops from molecule synthesis and animal testing. This new paradigm aims to evaluate AI techniques in scientific contexts, moving beyond chasing precision/recall scores at leaderboards which are prevalent in the current computer science community.

• 
  
  Karen Livescu (Toyota Technological Institute at Chicago)
  On the (co-)evolution of universal written, spoken, and signed language processing
  Bio Abstract

Karen Livescu is a Professor at TTI-Chicago, where she has been since 2008. Prior to TTIC, she did her PhD and postdoc at MIT. She is a Fellow of the IEEE and ISCA. She has served as a program chair/co-chair for ICLR, Interspeech, and ASRU, and as an Associate Editor for TACL, IEEE T-PAMI, and several other journals. Her group's work spans a variety of topics in spoken, written, and signed language processing, with a particular interest in representation learning, cross-modality learning, and low-resource settings.

Natural language processing research has evolved over the past few years from mainly task-specific models, then to task-independent representation models fine-tuned for various tasks, and finally to fully task-independent language models. This progression addresses a desire for universality in the sense of handling arbitrary tasks in the same model. Another dimension of universality is the ability to serve arbitrary types of language users, regardless of their choice of language, dialect, or other individual properties. Progress toward universality has historically been addressed largely independently in separate research communities focusing on written, spoken, and signed language, although they share many similarities. This talk will trace the recent progress toward universality in these three language modalities, while highlighting a few pieces of recent work.

• 
  
  David Mortensen (Carnegie Mellon University)
  The reconstruction will not be supervised
  Bio Abstract

David R. Mortensen is an Assistant Research Professor in the Language Technologies Institute at Carnegie Mellon University. He received his PhD in Linguistics from the University of California at Berkeley and held a position as an Assistant Professor of Linguistics at the University of Pittsburgh before transitioning to CMU, computational linguistics, and NLP. His work sits at the intersection between natural language processing, speech processing, phonology, morphology, and language change.

In the 19th century, European linguists discovered that it was possible to reconstruct earlier, unattested languages in a reproducible fashion by comparing their descendants (the Comparative Method). Starting in the 1960s, multiple attempts have been made to implement the Comparative Method computationally, to assist linguists in reconstructing ancestors for the hundreds of language families existing today. However, these efforts have never achieved parity with a first-year student of historical linguistics. In particular, these models have relied on direct or indirect supervision (in contrast to linguistics students, who are able to operate without supervision). I present an operationalization of the Comparative Method in terms of information and show how two different approaches to this domain move the field closer to unsupervised reconstruction by taking seriously the Comparative Method's tenets. First, I show that by forcing models to converge towards a bijective relationship between cognate sets (inputs) and reconstructions (outputs), the need for supervision from example reconstructions can be greatly reduced. Second, I demonstrate that sound laws, the rules that encode systematic changes in the pronunciation of words, can be induced automatically and in a data-efficient fashion using code language models (by treating the problem as a Programming by Example—PbE—task).

Getting to South Bend and Notre Dame

• From Chicago, the South Shore Line is an easy and inexpensive way to get to South Bend airport, from which it is about a 10 minute taxi ride to Notre Dame.
• For information about parking on Notre Dame's campus, please see: Guest & Visitor Parking.
• We provide a self-directed ride finding sheet here.

Staying in South Bend

• Morris Inn (0.03 miles).
• Embassy Suites (0.5 miles)
• Fairfield Inn (0.6 miles)
• Ivy Court (1.2 miles)
• Inn at Saint Mary's (2.1 miles)
• Hilton Garden Inn (2.2 miles)

We provide a self-directed roommate finding sheet here.

A restaurant guide can be found here.

Contact

Please contact msld25-list@nd.edu for questions and concerns.

Organizers

Sponsors