Seojin Lee


pdf bib
What, When, and How to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue
Deuksin Kwon | Sunwoo Lee | Ki Hyun Kim | Seojin Lee | Taeyoon Kim | Eric Davis
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)

This paper presents a method for building a personalized open-domain dialogue system to address the WWH (WHAT, WHEN, and HOW) problem for natural response generation in a commercial setting, where personalized dialogue responses are heavily interleaved with casual response turns. The proposed approach involves weighted dataset blending, negative persona information augmentation methods, and the design of personalized conversation datasets to address the challenges of WWH in personalized, open-domain dialogue systems. Our work effectively balances dialogue fluency and tendency to ground, while also introducing a response-type label to improve the controllability and explainability of the grounded responses. The combination of these methods leads to more fluent conversations, as evidenced by subjective human evaluations as well as objective evaluations.


pdf bib
An Evaluation Dataset and Strategy for Building Robust Multi-turn Response Selection Model
Kijong Han | Seojin Lee | Dong-hun Lee
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Multi-turn response selection models have recently shown comparable performance to humans in several benchmark datasets. However, in the real environment, these models often have weaknesses, such as making incorrect predictions based heavily on superficial patterns without a comprehensive understanding of the context. For example, these models often give a high score to the wrong response candidate containing several keywords related to the context but using the inconsistent tense. In this study, we analyze the weaknesses of the open-domain Korean Multi-turn response selection models and publish an adversarial dataset to evaluate these weaknesses. We also suggest a strategy to build a robust model in this adversarial environment.