← Search

Quanjie Han

2 accepted papers

2025

Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation

ICASSP 2025accepted

Open-domain Question Answering (QA) has garnered substantial interest by combining the advantages of faithfully retrieved passages and relevant passages generated through Large Language Models (LLMs). However, there is a lack of definitive labels available to pair these sources of knowledge. In orde…

Cited by 0SourceScholar
2024

Label Dependencies-Aware Set Prediction Networks for Multi-Label Text Classification

ICASSP 2024accepted

Multi-label text classification involves extracting all relevant labels from a sentence. Given the unordered nature of these labels, we propose approaching the problem as a set prediction task. To address the correlation between labels, we leverage Graph Convolutional Networks and construct an adjac…

Cited by 0SourceScholar