Information Extraction and Knowledge Acquisition

Time: Wednesday and Friday 2pm-3:15pm

Place: Online Live

Instructor: Prof. Heng Ji (Email: hengji@illinois.edu; Office: Online; Office hours: Wednesday and Friday 3:15pm-3:45pm; need to sign up in advance)

TA: Xiaoman Pan (xiaoman6@illinois.edu) (Office hours: Wednesday and Friday 3:15pm-3:45pm; need to sign up in advance)

Lectures and Schedules

Date

Lecture

Reading

Assignment

08/26

Overview, Name Tagging

Entity Discovery and Linking


08/28

Fine-grained Entity Extraction


09/02

Fine-grained Entity Extraction


09/04

Combining Symbolic Semantics and Distributional Semantics for Entity Linking


09/09

Low-resource Language EDL



09/10

Low-resource language EDL



09/15

Document-Level Joint IE



09/17

Document-Level Joint IE



Assignment 1
(due on TBA)

09/25

Biomedical IE



09/30

6pm-8pm

Makeup 3403


Biomedical IE


10/02


Event Schema Induction


Assignment 2 (due on TBA)

10/04


Event Schema Induction 



10/09

Event and Time Representation



10/11

Project Proposal Presentation



Assignment 3
(due on TBA)

10/16

Project Proposal



10/18

Event and Time Representation



10/23


Event Time Prediction



10/28

Event Time Prediction



10/30


Multimedia IE



11/04

Multimedia IE



11/06


IE for Question Answering



11/11


Misinformation Detection



First Paper Draft due
(due on TBA)

11/13


Misinformation Correction



First Paper Draft due
(due on TBA)

11/18

Paper Peer Review



11/20

Paper Peer Review



12/02

Final Project Open-House


12/04

Final Project Open-House


12/09

Final Project Open-House


Final Paper Due

Course Description

This is an advanced research-centric course to introduce the most up-to-date techniques in Information Extraction and Knowledge Acquisition, which aim to create the next generation of information access in which humans can communicate with computers in any natural language beyond keyword search, and computers can discover accurate, concise, and trustable information and knowledge embedded in big data from heterogeneous sources. We will select ten trending topics such as deep neural networks for Information Extraction, never-ending knowledge acquisition, zero-shot learning for cross-domain transfer. and give a comprehensive overview for each topic. We will review where we have been (the most successful methods in literature),   and where we are going (the remaining challenges, and novel methods to tackle these challenges). The target audience of this course is PhD students who do thesis research related to these topics. We also expect to invite several top researchers in this field to give guest lectures. The goal is for each student to have at least one solid paper submission ready at the end of this course. We will select classic papers about each topic and ask students to duplicate the core algorithms and even advance state-of-the-art with new ideas. We also aim to strengthen everyone’s presentation and writing skills, so we will do peer review on the presentations and paper submissions. 


Grading

The instructor will write most of the slides and hand-outs, give survey about the best papers from

. The following books may provide some useful background:


Prerequisites:

Class Policy

Mailing List

A mailing list "ie-2020“ will be created.