Papers by Minji Jung

4 papers
Debiasing Event Understanding for Visual Commonsense Tasks (2022.findings-acl)

Copied to clipboard

Challenge: a recent study shows that object-based event understanding is purely likelihood-based, leading to incorrect event prediction.
Approach: They propose to mitigate object-based event understanding by optimizing aggregation with association-based prediction.
Outcome: The proposed approach improves visual commonsense reasoning tasks by combining do-calculus with association-based prediction.
Enhancing Complex Reasoning in Knowledge Graph Question Answering through Query Graph Approximation (2025.findings-acl)

Copied to clipboard

Challenge: Existing knowledge-grounded question answering frameworks lack essential triplets related to the questions . Existing approaches to knowledge-based QA are incomplete in the context of KGs .
Approach: They propose a framework to provide answers to structured queries by leveraging Knowledge Graphs.
Outcome: The proposed framework outperforms existing methods on QA tasks where KGs are incomplete . the framework is based on a set of data from a dataset of QA questions .
Retrieval-augmented Video Encoding for Instructional Captioning (2023.findings-acl)

Copied to clipboard

Challenge: Instructional videos provide a detailed multimodal context of each procedure in instruction. key-object degeneracy is a problem for machine systems, causing incorrect captions.
Approach: They propose a retrieval-based framework to augment the model representations in the presence of key-object degeneracy.
Outcome: The proposed framework can be extended over baselines using modalities with key-object degeneracy.
Is Prompt Transfer Always Effective? An Empirical Study of Prompt Transfer for Question Answering (2024.naacl-short)

Copied to clipboard

Challenge: Prompt tuning is an efficient method for initializing pre-trained models . but initialization of prompts is sensitive when the model size is small .
Approach: They propose a method to measure catastrophic forgetting by analyzing prompts for the first time . they characterize a question answering task based on answer format and prompt initialization .
Outcome: The proposed approach can help deepen understanding of prompt tuning.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations