Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers coreference resolution, a natural language processing task that involves identifying when two or more expressions in text refer to the same entity. The instructor discusses the challenges of mention detection, different coreference resolution models, and the current state-of-the-art neural systems. The lecture also explores the applications of coreference resolution in full text understanding, machine translation, and dialogue systems. Various linguistic concepts related to coreference, anaphora, and cataphora are explained, along with traditional algorithms like Hobbs' naive algorithm. The lecture concludes with an overview of end-to-end neural coreference models and the latest advancements using BERT-based approaches.
This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.
Watch on Mediaspace