[Seminar] Character Mining: Machine Comprehension on Multiparty Dialogues

최진호
교수
Emory University
Date: 
Tuesday, May 23rd 2017, 4:00pm - Tuesday, May 23rd 2017, 5:00pm
Location: 
302-309/1

■ 호스트: 장병탁 교수(x1833, 880-1833) ■ 문의: 이유미 880-1847

Summary

This seminar presents the Character Mining project that extracts and infers various information about individual characters in multiparty dialogues. 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 crossdomain document retrieval. 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 dialogues. We introduce the agglomerative convolutional neural network model that gives the F1 score of 86.76% and the accuracy of 95.30% for this task. Emotion detection classifies each utterance in the dialogues to one of seven emotions, that are 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, cross-domain document retrieval is challenged, where the target documents are dialogues, and the queries are sentences describing events in those dialogues. We suggest a structure reranking model to improve the initial ranking from a search engine by utilizing syntactic and semantic structures, which shows an over 4% improvement.

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 Amazon Research Grant.