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 syntactic structure, dependency parsing, and neural network transition-based parsing. It explains the two views of linguistic structure, constituency, and dependency parsing, showing how words combine into phrases and how dependency structure shows which words depend on each other. The lecture also delves into the history of dependency grammar and parsing, highlighting the dominance of dependency structure in certain regions and its importance in inflected languages. It discusses methods of dependency parsing, such as dynamic programming, graph algorithms, and constraint satisfaction, and explores the concept of projectivity in parsing. The lecture concludes with an overview of graph-based dependency parsers and the advancements in transition-based parsing using neural network models.
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