Utilizing Text Structure for Information Extraction

Amir Veyseh
Date and time: 
Wed, Mar 3 2021 - 12:00pm to 1:30pm
Amir Veyseh
University of Oregon
  • Thien Nguyen (Chair)
  • Thanh Nguyen
  • Humphrey Shi

Information Extraction (IE) is one of the important fields of natural language processing (NLP) with the primary goal of creating structured knowledge from unstructured text. In more than two decades, IE has gained a lot of attention and many new tasks and models have been proposed. Moreover, with the proliferation of deep learning and neural nets in recent years, the advanced deep models have brought about a surge in the performance of IE models. Among others, some of the existing deep models resort to structure-based modeling whose goal is to exploit the structure of the text (i.e., interactions of different parts of the text) or external structures (e.g., a knowledge base). In this talk, I will review the structure-based deep models proposed for various IE tasks and also other related NLP tasks. Finally, I will discuss the limitations of the existing models and the potentials for future work.