1 code implementation • NAACL 2022 • Joosung Lee, Wooin Lee
We introduce CoMPM, which combines the speaker’s pre-trained memory with the context model, and find that the pre-trained memory significantly improves the performance of the context model.
no code implementations • 25 Mar 2024 • Joosung Lee, jinhong Kim
The second strategy is to enhance the facets by combining Large Language Model (LLM) and the small model.
1 code implementation • 10 Oct 2023 • Joosung Lee, Minsik Oh, Donghun Lee
Our system can function as a standard open-domain chatbot if persona information is not available.
1 code implementation • 13 Feb 2023 • Minsik Oh, Joosung Lee, Jiwei Li, Guoyin Wang
Identifying relevant persona or knowledge for conversational systems is critical to grounded dialogue response generation.
1 code implementation • 15 Jun 2022 • Joosung Lee
That is, instead of using a given label as a one-hot encoding, we construct a grayscale label by measuring scores for different emotions.
Ranked #4 on Emotion Recognition in Conversation on DailyDialog
1 code implementation • 10 Dec 2021 • Joosung Lee, Kijong Han
This paper presents our work on the Situated Interactive MultiModal Conversations 2. 0 challenge held at Dialog State Tracking Challenge 10.
1 code implementation • EMNLP 2021 • Kijong Han, Seojin Lee, Wooin Lee, Joosung Lee, Dong-hun Lee
Multi-turn response selection models have recently shown comparable performance to humans in several benchmark datasets.
1 code implementation • 26 Aug 2021 • Joosung Lee, Wooin Lee
We introduce CoMPM, which combines the speaker's pre-trained memory with the context model, and find that the pre-trained memory significantly improves the performance of the context model.
Ranked #5 on Emotion Recognition in Conversation on DailyDialog
no code implementations • 20 Jul 2021 • Joosung Lee
We present a simple and effective way to generate a variety of paraphrases and find a good quality paraphrase among them.
1 code implementation • RANLP 2021 • Joosung Lee
Our study focuses on language generation by considering various information representing the meaning of utterances as multiple conditions of generation.
1 code implementation • INLG (ACL) 2020 • Joosung Lee
The first stage is to delete attribute markers of a sentence directly through a classifier.
no code implementations • 7 Jan 2020 • Joosung Lee, Sangwon Hwang, Kyungjae Lee, Woo Jin Kim, Junhyeop Lee, Tae-young Chung, Sangyoun Lee
Visual odometry is an essential key for a localization module in SLAM systems.