Jin Yea Jang — accepted AI-conference papers

2024

Minimal Yet Big Impact: How AI Agent Back-channeling Enhances Conversational Engagement through Conversation Persistence and Context Richness

EMNLP 2024finding

The increasing use of AI agents in conversational services, such as counseling, highlights the importance of back-channeling (BC) as an active listening strategy to enhance conversational engagement. BC improves conversational engagement by providing timely acknowledgments and encouraging the speake…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2021

A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systems

San Kim, Jin Yea Jang, Minyoung Jung, Saim Shin

EMNLP 2021finding

Research on open-domain dialogue systems that allow free topics is challenging in the field of natural language processing (NLP). The performance of the dialogue system has been improved recently by the method utilizing dialogue-related knowledge; however, non-English dialogue systems suffer from re…

Cited by 30 Source ↗PDF ↗code ↗Scholar ↗

2021

BPM_MT: Enhanced Backchannel Prediction Model using Multi-Task Learning

Jin Yea Jang, San Kim, Minyoung Jung, Saim Shin, Gahgene Gweon

EMNLP 2021main

Backchannel (BC), a short reaction signal of a listener to a speaker’s utterances, helps to improve the quality of the conversation. Several studies have been conducted to predict BC in conversation; however, the utilization of advanced natural language processing techniques using lexical informatio…

Cited by 30 Source ↗PDF ↗code ↗Scholar ↗