GVU Center Brown Bag Seminar: Jinho Choi "Character Mining: Machine Comprehension on Multiparty Dialogue"

*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************

Event Details
  • Date/Time:
    • Thursday March 1, 2018 - Friday March 2, 2018
      11:30 am - 12:59 pm
  • Location: Technology Square Research Building, Atlanta, GA
  • Phone:
  • URL:
  • Email:
  • Fee(s):
    N/A
  • Extras:
    Free food
Contact

gvu@cc.gatech.edu

Summaries

Summary Sentence: This seminar will discuss the Character Mining project and its goal to develop a machine comprehension system that understands human conversations.

Full Summary: This talk presents the Character Mining project that extracts and infers various information about individual characters in multiparty dialogue.

Media
  • Jinho Choi Photo Jinho Choi Photo
    (image/png)

ABSTRACT

This talk presents the Character Mining project that extracts and infers various information about individual characters in multiparty dialogue. The long-term goal of this project is to develop a machine comprehension system that understands human conversations. Currently, this project focuses on three tasks, character identification, emotion detection, and reading comprehension. Character identification is an entity linking task that identifies each mention referring to a human (e.g., she, mom) as a certain character in the dialogue. We introduce the agglomerative convolutional neural network model that gives the F1 score of 86.76% for this task. Emotion detection classifies each utterance in the dialogues to one of seven emotions (sad, mad, scared, powerful, peaceful, joyful, and neutral). We introduce the sequence-based convolutional neural network model that shows the accuracies of 37.51% and 53.76% for fine and coarse-grained emotions, respectively. Finally, reading comprehension is challenged, where the input documents are dialogues, and the queries are sentences describing events in these dialogues. We suggest several attention-based deep neural models showing accuracies over 72% and robust performance for long documents.

SPEAKER BIO

Jinho Choi is an assistant professor in the Department of Mathematics and Computer Science, the Institute of Quantitative Theory and Methods, and the Program of Linguistics at Emory University. He obtained a B.A. in Computer Science and Mathematics (dual degree) from Coe College in 2002, a M.S.E. in Computer and Information Science from the University of Pennsylvania in 2003 with Mitchell Marcus, a Ph.D. in Computer Science and Cognitive Science (joint degree) from the University of Colorado Boulder in 2012 with Martha Palmer, and did his postdoctoral work at the University of Massachusetts Amherst in 2014 with Andrew McCallum. He was a full-time lecturer in the Department of Computer Science at the Korea Military Academy from 2004 to 2007 while he was serving his military duty in South Korea. He was a R&D team lead of the Amelia project, the next generation machine reading system developed at IPsoft Inc. He is the founder of the Natural Language Processing Research lab at Emory University. He has one several awards and grants including the Yahoo Academic Career Enhancement Awards and the AWS Machine Learning Research Grant.

Additional Information

In Campus Calendar
Yes
Groups

GVU Center, IPaT, School of Interactive Computing

Invited Audience
Faculty/Staff, Public, Graduate students, Undergraduate students
Categories
Seminar/Lecture/Colloquium
Keywords
No keywords were submitted.
Status
  • Created By: Dorie Taylor
  • Workflow Status: Published
  • Created On: Feb 21, 2018 - 5:39pm
  • Last Updated: Feb 26, 2018 - 10:41am