Xinya Du - Towards Better Informed Extraction of Events from Documents скачать в хорошем качестве

Xinya Du - Towards Better Informed Extraction of Events from Documents

Xinya Du is a PhD student at Cornell University. This presentation is part of the 2021 Rising Stars in Data Science Workshop, presented by the Center for Data and Computing at the University of Chicago. The annual workshop celebrates and fast tracks the careers of exceptional data scientists at a critical inflection point in their career: the transition from PhD to postdoctoral scholar, research scientist, or tenure track position. For more information, visit: cdac.uchicago.edu/rising-stars/ ==== Towards Better Informed Extraction of Events from Documents Large amounts of text are written and published daily on-line. As a result, applications such as reading through the document to automatically extract useful information, and answering user questions have become increasingly needed for people’s efficient absorption of information. In this talk, I will focus on the problem of finding and organizing information about events and introduce my recent research on document-level event extraction. Firstly, I'll briefly summarize the high-level goal and several key challenges (including modeling context and better leveraging background knowledge), as well as my efforts to tackle them. Then I will focus on the work where we formulate event extraction as a question answering problem --- both to access relevant knowledge encoded in large models and to reduce the cost of human annotation required for training data creation/construction.