What we're about

Group for all Natural Language Processing (NLP) and Machine Learning (ML) researchers, students, practitioners and enthusiasts in the Ann Arbor and Detroit Areas who want to get together and discuss their interests and stay up-to-date on the latest developments in NLP. This is a place to discuss research, interests, practical application, emerging/disruptive technologies, trends and best practices. Also join the Ann Arbor ML/AI/Data Science community slack (#nlp):


Upcoming events (1)

Data to Text and Sports Natural Language Generation (NLG)

Link visible for attendees

Our November 9 program features an online presentation on Data to Text and Sports Natural Language Generation (NLG) by Ehud Reiter and Jorge Costa of Arria NLG.

They will describe data-to-text NLG including technologies with a focus on sports story-writing. Our speakers will discuss sports NLG goals, challenges, and approaches and describe system function at a high level with knowledge-based technologies. There are complications that include difficulties using neural language models in sports NLG because of accuracy and hallucination problems. Ehud and Jorge will talk about challenges getting high-quality data and how computer vision can be used to automatically extract useful game data (for the NLG system) from video data.

Ehud Reiter is a Professor of Computing Science at the University of Aberdeen and the Chief Scientist of Arria NLG. He has been working in natural language generation for 35 years and is one of the most cited and respected researchers in this field. Prof Reiter has a Google Scholar h-index of 54 and is currently chair of the ACL Special Interest Group on Generation (SIGGEN). For more information about Prof Reiter, see ehudreiter.com.

Jorge Costa is Senior Vice President of Sports Analytics at Arria Boost, the sports media division of Arria NLG. He has over 15 years of experience at the intersection of sports, analytics, and the communication of complex data. After starting his career at the NBA League Office, Jorge moved to the team side as Director of Research and Technology for the Detroit Pistons (NBA), where he led the development of decision-making analytics tools and processes for the team's front office. Today, Jorge and his team of data scientists build scalable storytelling solutions, serving multiple sports and content types.

By responding here, you acknowledge and consent to our Code of Conduct: We seek to provide a respectful, friendly, professional experience for everyone regardless of gender, sexual orientation, physical appearance, disability, age, race, and religion. We do not tolerate behavior that is harassing or degrading to any individual, in any form. Participants are responsible for knowing and abiding by these standards. We encourage all attendees to assist in creating a welcoming, safe, and respectful experience.

Past events (60)

Few-shot Learning with Retrieval Augmented Language Models

This event has passed

Photos (37)