← Search

Haeju Lee

2 accepted papers

2023

Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning

EMNLP 2023long findings

Prompt tuning, in which prompts are optimized to adapt large-scale pre-trained language models to downstream tasks instead of fine-tuning the full model parameters, has been shown to be particularly effective when the prompts are trained in the multi-task transfer learning setting. These methods gen…

Cited by 0SourcecodeScholar
2022

Learning to Embed Multi-Modal Contexts for Situated Conversational Agents

NAACL 2022findings

The Situated Interactive Multi-Modal Conversations (SIMMC) 2.0 aims to create virtual shopping assistants that can accept complex multi-modal inputs, i.e. visual appearances of objects and user utterances. It consists of four subtasks, multi-modal disambiguation (MM-Disamb), multi-modal coreference…

Cited by 13SourcePDFScholar