activity
20182020
collaborators

6 papers

cs.CL2020

Auxiliary Sequence Labeling Tasks for Disfluency Detection

Dongyub Lee, Byeongil Ko, Myeong Cheol Shin +5

Detecting disfluencies in spontaneous speech is an important preprocessing step in natural language processing and speech recognition applications. Existing works for disfluency de…

cs.CL2020

Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection

Taesun Whang, Dongyub Lee, Dongsuk Oh +4

In this paper, we study the task of selecting the optimal response given a user and system utterance history in retrieval-based multi-turn dialog systems. Recently, pre-trained lan…

cs.CL2020

Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization

Dongyub Lee, Myeongcheol Shin, Taesun Whang +5

Text summarization refers to the process that generates a shorter form of text from the source document preserving salient information. Many existing works for text summarization a…

cs.CL2019

An Effective Domain Adaptive Post-Training Method for BERT in Response Selection

Taesun Whang, Dongyub Lee, Chanhee Lee +3

We focus on multi-turn response selection in a retrieval-based dialog system. In this paper, we utilize the powerful pre-trained language model Bi-directional Encoder Representatio…

cs.CL2019

EmotionX-KU: BERT-Max based Contextual Emotion Classifier

Kisu Yang, Dongyub Lee, Taesun Whang +2

We propose a contextual emotion classifier based on a transferable language model and dynamic max pooling, which predicts the emotion of each utterance in a dialogue. A representat…

cs.CL2018

Character-Level Feature Extraction with Densely Connected Networks

Chanhee Lee, Young-Bum Kim, Dongyub Lee +1

Generating character-level features is an important step for achieving good results in various natural language processing tasks. To alleviate the need for human labor in generatin…