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

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 gives an overview tutorial (2pm-2:50pm), followed by Q/A and discussions (2:50pm-3:15pm).
• 3 Assignments (15pts each): participate in shared tasks and submit through Codalab, the grades will be based on your system’s rank in the class. If a submission is successfully complete then it will get 10 basic score, and then the additional score is based on the system's relative rank in the class between [0, 5]
• Final Paper submitted to ACL2021 (55pts): you can either continue working on one of the assignments and focus on novel methods, or choose a new topic to work on. we will host open-house poster session and select a paper for best paper.
• 
  
• Course Materials

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

• ACL Papers: ACL Anthology.

. The following books may provide some useful background:

• Speech and Language Processing, Daniel Jurafsky and James Martin, Prentice-Hall (second edition).
• Christopher D. Manning and Hinrich Schutze. Foundations of Statistical Natural Language Processing. MIT Press.
• Christopher M. Bishop. Pattern Recognition and Machine Learning.
• Trevor Hastie, Robert Tibshirani and Jerome Friedman. The Elements of Statistical Learning.
• Jiawei Han, Micheline Kamber, and Jian Pei, Data Mining: Concepts and Techniques, 3^rd edition, Morgan Kaufmann

Prerequisites:

• Programming in Python
• Already took NLP and machine learning courses
• Familiar with Probability and Statistics
• research background in NLP or related fields; it's targeted for students who work on related areas. Extensive research background is expected.
• interests in languages and lingusitics
• solid background in algorithms, probabilities
• good programming skills
• sufficient mathematical background

Class Policy

• Restricted Academic Integrity
• NO Incompleteness are accepted
• NO Late Assignments are accepted
• Turn on camera; actively participate in discussions
• Don't come late to the class, if you are late more than 10 minutes, simply skip it in order not to disturb the lecture

Mailing List

ie-2020@lists.cs.illinois.edu