Papers by Xinhang Li

2 papers
Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and Grounding (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for fine-grained content extraction are limited by long-tailed distribution of textual entity categories and performance of object detectors.
Approach: They propose a multi-granularity entity recognition module and a reranking module to integrate hierarchical information of entity categories, visual cues, and external textual resources collectively.
Outcome: The proposed framework achieves state-of-the-art on the fine-grained content extraction task.
Visualization Recommendation with Prompt-based Reprogramming of Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Traditional visualization recommendations require extensive manual maintenance and yet fail to fully comprehend tabular data.
Approach: They propose a hierarchical table prompt-based reprogramming framework that integrates tabular data into LLMs through a strategically crafted prompt learning method.
Outcome: The proposed framework achieves state-of-the-art performance and will be made publicly available upon acceptance.

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