Keynote Talks
|
|
Full Professor (Chair) for AI and Computational Linguistics at LMU Munich.
Research lab lead of the Munich AI and Natural Language Processing lab (MaiNLP)
and co-director of the Center for Information and Language Processing (CIS).
Also, professor (part-time) at ITU (IT University of Copenhagen), NLP North lab. |
Title: Human-centric Natural Language Processing
Abstract:
Despite the recent success of Natural Language Processing (NLP), driven by advances in large language models (LLMs) trained on enormous amounts of data, there are many challenges ahead to make NLP more human-facing and inclusive. For instance, low-resource languages, non-standard data and dialects pose particular challenges, due to the high variability in language paired with low availability of data. Moreover, while language varies along many dimensions, evaluation today largely focuses on standard splits, and assumes the existence of a single correct answer. In this talk I will survey some of the challenges, and outline some potential solutions, discussing work on cross-lingual transfer learning, NLP for dialects, and data-centric NLP, which includes learning in light of human label variation.
|
|
Claudia Hauff is a Staff Research Scientist at Spotify, based in the Netherlands. She has a PhD (2010 from the University of Twente) in Information Retrieval and spent more than 10 years in academia at TU Delft, leading a team of junior researchers on a wide range of IR topics including conversational search, collaborative search, search as learning and neural IR.
|
Title: On the Challenges of Podcast Search at Spotify
Abstract:
Online music streaming is enjoying ever-growing popularity over the past decades, enabled by the abundance of music content in digital format and online streaming services. In recent years, podcasts (a talk-focused media format) have witnessed a rapid growth among listeners. Podcasts come in many forms and sizes. They range from 20-minute daily meditation sessions, weekly recaps of global news, to interviews with celebrities, and hosts bantering with each other for hours. More and more streaming services are now expanding their catalogs to support both music and podcasts on the same platform. This setup requires an effective aggregated search system to assemble information from heterogeneous information sources and content types into one result interface in order to support diverse information needs. In this talk I will present a number of open challenges in this domain.
