Papers by Minsik Oh
PK-ICR: Persona-Knowledge Interactive Multi-Context Retrieval for Grounded Dialogue (2023.emnlp-main)
Copied to clipboard
| Challenge: | Identifying relevant persona or knowledge for conversational systems is difficult, but recent work has shown that it is more realistic to optimize for concrete persona. |
| Approach: | They propose a persona-knowledge dual context retrieval method that utilizes all dialogue contexts simultaneously. |
| Outcome: | The proposed method performs zero-shot top-1 knowledge retrieval and precise persona scoring. |
Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings (2026.acl-long)
Copied to clipboard
| Challenge: | Annotating and gathering utterance relationships in dialogues is difficult, while token-level annotations, entities, slots and templates, are much easier to obtain. |
| Approach: | They propose a template-aware augmentation method that utilizes template information to learn utterance embeddings via self-supervised contrastive learning framework. |
| Outcome: | The proposed method improves on five benchmark dialogue datasets and shows that it is more efficient than previous SOTA methods. |
P5: Plug-and-Play Persona Prompting for Personalized Response Selection (2023.emnlp-main)
Copied to clipboard
| Challenge: | a plug-and-play persona prompting system can be used to generate personalized responses for real applications . a recent study shows that dialog context alone is insufficient for personalized response selection . |
| Approach: | They propose a plug-and-play persona prompting method that can be used in real applications . they show that the method performs well in the zero-shot setting . |
| Outcome: | The proposed method performs well in the zero-shot setting, and can be fine-tuned for even better performance. |