Keynote Speakers

Bio: Jose Camacho-Collados is a Professor at Cardiff University, leading the Cardiff NLP group. Before joining Cardiff University, he completed his PhD in Sapienza University of Rome and was a Google AI PhD Fellow. Until recently, his research has focused on various semantics aspects in NLP with a distributional perspective. He wrote the “Embeddings in Natural Language Processing" book and is the General Chair of *SEM 2024. More related to the topic of the talk, in the last few years Jose has been working in social media analysis and applications, developing NLP tools specifically targeted to this domain such as TweetNLP.

Jose was born in Granada (Spain), where he was raised and lived for the first 22 years of his life and still visits regularly. He studied a 5-year BSc degree in Mathematics at the University of Granada and was a visiting scholar at the same university in 2021/2022.

Abstract: Social media represents a fundamental tool to understand society interactions in the 21st century. Despite the large amount of information generated in social media platforms, understanding what is going on is not an easy task, even after the significant progress in AI and Natural Language Processing (NLP) in recent years. Its multilingual, dynamic, informal and multimodal nature means that standard techniques are seldom optimal.

In this talk, I will summarise some of the recent advances on social media processing, and in particular the development of specialised language models and unified benchmarks. Then, I will discuss our latest research that addresses the temporal and dynamic nature in social media, and how this plays an important role in downstream applications such as hate speech detection. Finally, I will introduce TweetNLP, one of our latest projects stemming from an international partnership between academia and industry, and some of its applications for computational social science research such as sentiment analysis, hate speech detection, topic classification, and named entity recognition.

Bio: Laura Sevilla is an associate professor at the University of Edinburgh since 2019, where she leads her group that focuses in computer vision and machine learning.  Before then she was a researcher at Facebook Research in California and a postdoc at the Max Planck Institute in Germany. She obtained her PhD from the University of Massachusetts Amherst in 2015. During this time, she has worked in video understanding, from optical flow to object tracking, video captioning and perception for robotics. She has been awarded the Google Research Scholar Award, and the Google Faculty Award.

Laura was born in Jaén, grew up in Linares (Jaén) and Castril (Granada) and did her undergraduate degree in Computer Engineering at the University of Granada.

Abstract: Video Understanding is a fundamental ability of intelligent systems, from robots to drones, virtual assistants and self-driving cars. Video is an extremely powerful source of information, it’s essentially the difference between going about your day with your days open or closed. At the same time it is extremely challenging, and as a result it lags years behind other areas like text or even image understanding. What is holding us back? From efficiency bottlenecks to improving our tasks, I will discuss our main challenges in video understanding, as well as describe principles to address them.